omni.isaac.lab.envs

Sub-package for environment definitions.

Environments define the interface between the agent and the simulation. In the simplest case, the environment provides the agent with the current observations and executes the actions provided by the agent. However, the environment can also provide additional information such as the current reward, done flag, and information about the current episode.

There are two types of environment designing workflows:

• Manager-based: The environment is decomposed into individual components (or managers) for different aspects (such as computing observations, applying actions, and applying randomization. The users mainly configure the managers and the environment coordinates the managers and calls their functions.

• Direct: The user implements all the necessary functionality directly into a single class directly without the need for additional managers.

Based on these workflows, there are the following environment classes for single and multi-agent RL:

Single-Agent RL:

• ManagerBasedEnv: The manager-based workflow base environment which only provides the agent with the current observations and executes the actions provided by the agent.

• ManagerBasedRLEnv: The manager-based workflow RL task environment which besides the functionality of the base environment also provides additional Markov Decision Process (MDP) related information such as the current reward, done flag, and information.

• DirectRLEnv: The direct workflow RL task environment which provides implementations for implementing scene setup, computing dones, performing resets, and computing reward and observation.

Multi-Agent RL (MARL):

• DirectMARLEnv: The direct workflow MARL task environment which provides implementations for implementing scene setup, computing dones, performing resets, and computing reward and observation.

For more information about the workflow design patterns, see the Task Design Workflows section.

Submodules

mdp	Sub-module with implementation of manager terms.
ui	Sub-module providing UI window implementation for environments.

Classes

ManagerBasedEnv	The base environment encapsulates the simulation scene and the environment managers for the manager-based workflow.
ManagerBasedEnvCfg	Base configuration of the environment.
ManagerBasedRLEnv	The superclass for the manager-based workflow reinforcement learning-based environments.
ManagerBasedRLEnvCfg	Configuration for a reinforcement learning environment with the manager-based workflow.
DirectRLEnv	The superclass for the direct workflow to design environments.
DirectRLEnvCfg	Configuration for an RL environment defined with the direct workflow.
DirectMARLEnv	The superclass for the direct workflow to design multi-agent environments.
DirectMARLEnvCfg	Configuration for a MARL environment defined with the direct workflow.
ViewerCfg	Configuration of the scene viewport camera.

Manager Based Environment

class omni.isaac.lab.envs.ManagerBasedEnv

The base environment encapsulates the simulation scene and the environment managers for the manager-based workflow.

While a simulation scene or world comprises of different components such as the robots, objects, and sensors (cameras, lidars, etc.), the environment is a higher level abstraction that provides an interface for interacting with the simulation. The environment is comprised of the following components:

• Scene: The scene manager that creates and manages the virtual world in which the robot operates. This includes defining the robot, static and dynamic objects, sensors, etc.

• Observation Manager: The observation manager that generates observations from the current simulation state and the data gathered from the sensors. These observations may include privileged information that is not available to the robot in the real world. Additionally, user-defined terms can be added to process the observations and generate custom observations. For example, using a network to embed high-dimensional observations into a lower-dimensional space.

• Action Manager: The action manager that processes the raw actions sent to the environment and converts them to low-level commands that are sent to the simulation. It can be configured to accept raw actions at different levels of abstraction. For example, in case of a robotic arm, the raw actions can be joint torques, joint positions, or end-effector poses. Similarly for a mobile base, it can be the joint torques, or the desired velocity of the floating base.

• Event Manager: The event manager orchestrates operations triggered based on simulation events. This includes resetting the scene to a default state, applying random pushes to the robot at different intervals of time, or randomizing properties such as mass and friction coefficients. This is useful for training and evaluating the robot in a variety of scenarios.

The environment provides a unified interface for interacting with the simulation. However, it does not include task-specific quantities such as the reward function, or the termination conditions. These quantities are often specific to defining Markov Decision Processes (MDPs) while the base environment is agnostic to the MDP definition.

The environment steps forward in time at a fixed time-step. The physics simulation is decimated at a lower time-step. This is to ensure that the simulation is stable. These two time-steps can be configured independently using the ManagerBasedEnvCfg.decimation (number of simulation steps per environment step) and the ManagerBasedEnvCfg.sim.dt (physics time-step) parameters. Based on these parameters, the environment time-step is computed as the product of the two. The two time-steps can be obtained by querying the physics_dt and the step_dt properties respectively.

Methods:

__init__(cfg)	Initialize the environment.
load_managers()	Load the managers for the environment.
reset([seed, options])	Resets all the environments and returns observations.
step(action)	Execute one time-step of the environment's dynamics.
seed([seed])	Set the seed for the environment.
close()	Cleanup for the environment.

Attributes:

num_envs	The number of instances of the environment that are running.
physics_dt	The physics time-step (in s).
step_dt	The environment stepping time-step (in s).
device	The device on which the environment is running.

__init__(cfg: ManagerBasedEnvCfg)

Initialize the environment.

参数:

cfg – The configuration object for the environment.

抛出:

RuntimeError – If a simulation context already exists. The environment must always create one since it configures the simulation context and controls the simulation.

property num_envs: int

The number of instances of the environment that are running.

property physics_dt: float

The physics time-step (in s).

This is the lowest time-decimation at which the simulation is happening.

property step_dt: float

The environment stepping time-step (in s).

This is the time-step at which the environment steps forward.

property device

The device on which the environment is running.

load_managers()

Load the managers for the environment.

This function is responsible for creating the various managers (action, observation, events, etc.) for the environment. Since the managers require access to physics handles, they can only be created after the simulator is reset (i.e. played for the first time).

备注

In case of standalone application (when running simulator from Python), the function is called automatically when the class is initialized.

However, in case of extension mode, the user must call this function manually after the simulator is reset. This is because the simulator is only reset when the user calls SimulationContext.reset_async() and it isn’t possible to call async functions in the constructor.

reset(seed: int | None = None, options: dict[str, Any] | None = None) → tuple[Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]], dict]

Resets all the environments and returns observations.

This function calls the _reset_idx() function to reset all the environments. However, certain operations, such as procedural terrain generation, that happened during initialization are not repeated.

参数:

• seed – The seed to use for randomization. Defaults to None, in which case the seed is not set.

• options –

  Additional information to specify how the environment is reset. Defaults to None.

  备注

  This argument is used for compatibility with Gymnasium environment definition.

返回:

A tuple containing the observations and extras.

step(action: torch.Tensor) → tuple[Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]], dict]

Execute one time-step of the environment’s dynamics.

The environment steps forward at a fixed time-step, while the physics simulation is decimated at a lower time-step. This is to ensure that the simulation is stable. These two time-steps can be configured independently using the ManagerBasedEnvCfg.decimation (number of simulation steps per environment step) and the ManagerBasedEnvCfg.sim.dt (physics time-step). Based on these parameters, the environment time-step is computed as the product of the two.

参数:

action – The actions to apply on the environment. Shape is (num_envs, action_dim).

返回:

A tuple containing the observations and extras.

static seed(seed: int = -1) → int

Set the seed for the environment.

参数:

seed – The seed for random generator. Defaults to -1.

返回:

The seed used for random generator.

close()

Cleanup for the environment.

class omni.isaac.lab.envs.ManagerBasedEnvCfg

Base configuration of the environment.

Attributes:

viewer	Viewer configuration.
sim	Physics simulation configuration.
seed	The seed for the random number generator.
decimation	Number of control action updates @ sim dt per policy dt.
scene	Scene settings.
observations	Observation space settings.
actions	Action space settings.
events	Event settings.
rerender_on_reset	Whether a render step is performed again after at least one environment has been reset.

Classes:

ui_window_class_type

BaseEnvWindow 的别名

viewer: ViewerCfg

Viewer configuration. Default is ViewerCfg().

sim: SimulationCfg

Physics simulation configuration. Default is SimulationCfg().

ui_window_class_type

BaseEnvWindow 的别名

seed: int | None

The seed for the random number generator. Defaults to None, in which case the seed is not set.

备注

The seed is set at the beginning of the environment initialization. This ensures that the environment creation is deterministic and behaves similarly across different runs.

decimation: int

Number of control action updates @ sim dt per policy dt.

For instance, if the simulation dt is 0.01s and the policy dt is 0.1s, then the decimation is 10. This means that the control action is updated every 10 simulation steps.

scene: InteractiveSceneCfg

Scene settings.

Please refer to the omni.isaac.lab.scene.InteractiveSceneCfg class for more details.

observations: object

Observation space settings.

Please refer to the omni.isaac.lab.managers.ObservationManager class for more details.

actions: object

Action space settings.

Please refer to the omni.isaac.lab.managers.ActionManager class for more details.

events: object

Event settings. Defaults to the basic configuration that resets the scene to its default state.

Please refer to the omni.isaac.lab.managers.EventManager class for more details.

rerender_on_reset: bool

Whether a render step is performed again after at least one environment has been reset. Defaults to False, which means no render step will be performed after reset.

• When this is False, data collected from sensors after performing reset will be stale and will not reflect the latest states in simulation caused by the reset.

• When this is True, an extra render step will be performed to update the sensor data to reflect the latest states from the reset. This comes at a cost of performance as an additional render step will be performed after each time an environment is reset.

Manager Based RL Environment

class omni.isaac.lab.envs.ManagerBasedRLEnv

基类：ManagerBasedEnv, Env

The superclass for the manager-based workflow reinforcement learning-based environments.

This class inherits from ManagerBasedEnv and implements the core functionality for reinforcement learning-based environments. It is designed to be used with any RL library. The class is designed to be used with vectorized environments, i.e., the environment is expected to be run in parallel with multiple sub-environments. The number of sub-environments is specified using the num_envs.

Each observation from the environment is a batch of observations for each sub- environments. The method step() is also expected to receive a batch of actions for each sub-environment.

While the environment itself is implemented as a vectorized environment, we do not inherit from gym.vector.VectorEnv. This is mainly because the class adds various methods (for wait and asynchronous updates) which are not required. Additionally, each RL library typically has its own definition for a vectorized environment. Thus, to reduce complexity, we directly use the gym.Env over here and leave it up to library-defined wrappers to take care of wrapping this environment for their agents.

备注

For vectorized environments, it is recommended to only call the reset() method once before the first call to step(), i.e. after the environment is created. After that, the step() function handles the reset of terminated sub-environments. This is because the simulator does not support resetting individual sub-environments in a vectorized environment.

Attributes:

is_vector_env	Whether the environment is a vectorized environment.
metadata	Metadata for the environment.
cfg	Configuration for the environment.
max_episode_length_s	Maximum episode length in seconds.
max_episode_length	Maximum episode length in environment steps.
device	The device on which the environment is running.
np_random	Returns the environment's internal _np_random that if not set will initialise with a random seed.
np_random_seed	Returns the environment's internal _np_random_seed that if not set will first initialise with a random int as seed.
num_envs	The number of instances of the environment that are running.
physics_dt	The physics time-step (in s).
step_dt	The environment stepping time-step (in s).
unwrapped	Returns the base non-wrapped environment.

Methods:

__init__(cfg[, render_mode])	Initialize the environment.
load_managers()	Load the managers for the environment.
step(action)	Execute one time-step of the environment's dynamics and reset terminated environments.
render([recompute])	Run rendering without stepping through the physics.
close()	Cleanup for the environment.
get_wrapper_attr(name)	Gets the attribute name from the environment.
has_wrapper_attr(name)	Checks if the attribute name exists in the environment.
reset([seed, options])	Resets all the environments and returns observations.
seed([seed])	Set the seed for the environment.
set_wrapper_attr(name, value)	Sets the attribute name on the environment with value.

is_vector_env: ClassVar[bool] = True

Whether the environment is a vectorized environment.

metadata: ClassVar[dict[str, Any]] = {'isaac_sim_version': omni.isaac.version.get_version, 'render_modes': [None, 'human', 'rgb_array']}

Metadata for the environment.

cfg: ManagerBasedRLEnvCfg

Configuration for the environment.

__init__(cfg: ManagerBasedRLEnvCfg, render_mode: str | None = None, **kwargs)

Initialize the environment.

参数:

• cfg – The configuration for the environment.

• render_mode – The render mode for the environment. Defaults to None, which is similar to "human".

property max_episode_length_s: float

Maximum episode length in seconds.

property max_episode_length: int

Maximum episode length in environment steps.

load_managers()

Load the managers for the environment.

This function is responsible for creating the various managers (action, observation, events, etc.) for the environment. Since the managers require access to physics handles, they can only be created after the simulator is reset (i.e. played for the first time).

备注

In case of standalone application (when running simulator from Python), the function is called automatically when the class is initialized.

However, in case of extension mode, the user must call this function manually after the simulator is reset. This is because the simulator is only reset when the user calls SimulationContext.reset_async() and it isn’t possible to call async functions in the constructor.

step(action: torch.Tensor) → tuple[Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]], torch.Tensor, torch.Tensor, torch.Tensor, dict]

Execute one time-step of the environment’s dynamics and reset terminated environments.

Unlike the ManagerBasedEnv.step class, the function performs the following operations:

1. Process the actions.

2. Perform physics stepping.

3. Perform rendering if gui is enabled.

4. Update the environment counters and compute the rewards and terminations.

5. Reset the environments that terminated.

6. Compute the observations.

7. Return the observations, rewards, resets and extras.

参数:

action – The actions to apply on the environment. Shape is (num_envs, action_dim).

返回:

A tuple containing the observations, rewards, resets (terminated and truncated) and extras.

render(recompute: bool = False) → np.ndarray | None

Run rendering without stepping through the physics.

By convention, if mode is:

• human: Render to the current display and return nothing. Usually for human consumption.

• rgb_array: Return an numpy.ndarray with shape (x, y, 3), representing RGB values for an x-by-y pixel image, suitable for turning into a video.

参数:

recompute – Whether to force a render even if the simulator has already rendered the scene. Defaults to False.

返回:

The rendered image as a numpy array if mode is “rgb_array”. Otherwise, returns None.

抛出:

• RuntimeError – If mode is set to “rgb_data” and simulation render mode does not support it. In this case, the simulation render mode must be set to RenderMode.PARTIAL_RENDERING or RenderMode.FULL_RENDERING.

• NotImplementedError – If an unsupported rendering mode is specified.

close()

Cleanup for the environment.

property device

The device on which the environment is running.

get_wrapper_attr(name: str) → Any

Gets the attribute name from the environment.

has_wrapper_attr(name: str) → bool

Checks if the attribute name exists in the environment.

property np_random: numpy.random.Generator

Returns the environment’s internal _np_random that if not set will initialise with a random seed.

返回:

Instances of np.random.Generator

property np_random_seed: int

Returns the environment’s internal _np_random_seed that if not set will first initialise with a random int as seed.

If np_random_seed was set directly instead of through reset() or set_np_random_through_seed(), the seed will take the value -1.

返回:

the seed of the current np_random or -1, if the seed of the rng is unknown

返回类型:

int

property num_envs: int

The number of instances of the environment that are running.

property physics_dt: float

The physics time-step (in s).

This is the lowest time-decimation at which the simulation is happening.

reset(seed: int | None = None, options: dict[str, Any] | None = None) → tuple[Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]], dict]

Resets all the environments and returns observations.

This function calls the _reset_idx() function to reset all the environments. However, certain operations, such as procedural terrain generation, that happened during initialization are not repeated.

参数:

• seed – The seed to use for randomization. Defaults to None, in which case the seed is not set.

• options –

  Additional information to specify how the environment is reset. Defaults to None.

  备注

  This argument is used for compatibility with Gymnasium environment definition.

返回:

A tuple containing the observations and extras.

static seed(seed: int = -1) → int

Set the seed for the environment.

参数:

seed – The seed for random generator. Defaults to -1.

返回:

The seed used for random generator.

set_wrapper_attr(name: str, value: Any)

Sets the attribute name on the environment with value.

property step_dt: float

The environment stepping time-step (in s).

This is the time-step at which the environment steps forward.

property unwrapped: Env[ObsType, ActType]

Returns the base non-wrapped environment.

返回:

The base non-wrapped gymnasium.Env instance

返回类型:

Env

class omni.isaac.lab.envs.ManagerBasedRLEnvCfg

基类：ManagerBasedEnvCfg

Configuration for a reinforcement learning environment with the manager-based workflow.

Classes:

ui_window_class_type

ManagerBasedRLEnvWindow 的别名

Attributes:

is_finite_horizon	Whether the learning task is treated as a finite or infinite horizon problem for the agent.
episode_length_s	Duration of an episode (in seconds).
rewards	Reward settings.
viewer	Viewer configuration.
sim	Physics simulation configuration.
seed	The seed for the random number generator.
decimation	Number of control action updates @ sim dt per policy dt.
scene	Scene settings.
observations	Observation space settings.
actions	Action space settings.
events	Event settings.
rerender_on_reset	Whether a render step is performed again after at least one environment has been reset.
terminations	Termination settings.
curriculum	Curriculum settings.
commands	Command settings.

ui_window_class_type

ManagerBasedRLEnvWindow 的别名

is_finite_horizon: bool

Whether the learning task is treated as a finite or infinite horizon problem for the agent. Defaults to False, which means the task is treated as an infinite horizon problem.

This flag handles the subtleties of finite and infinite horizon tasks:

• Finite horizon: no penalty or bootstrapping value is required by the the agent for running out of time. However, the environment still needs to terminate the episode after the time limit is reached.

• Infinite horizon: the agent needs to bootstrap the value of the state at the end of the episode. This is done by sending a time-limit (or truncated) done signal to the agent, which triggers this bootstrapping calculation.

If True, then the environment is treated as a finite horizon problem and no time-out (or truncated) done signal is sent to the agent. If False, then the environment is treated as an infinite horizon problem and a time-out (or truncated) done signal is sent to the agent.

备注

The base ManagerBasedRLEnv class does not use this flag directly. It is used by the environment wrappers to determine what type of done signal to send to the corresponding learning agent.

episode_length_s: float

Duration of an episode (in seconds).

Based on the decimation rate and physics time step, the episode length is calculated as:

episode_length_steps = ceil(episode_length_s / (decimation_rate * physics_time_step))

For example, if the decimation rate is 10, the physics time step is 0.01, and the episode length is 10 seconds, then the episode length in steps is 100.

rewards: object

Reward settings.

Please refer to the omni.isaac.lab.managers.RewardManager class for more details.

viewer: ViewerCfg

Viewer configuration. Default is ViewerCfg().

sim: SimulationCfg

Physics simulation configuration. Default is SimulationCfg().

seed: int | None

The seed for the random number generator. Defaults to None, in which case the seed is not set.

备注

The seed is set at the beginning of the environment initialization. This ensures that the environment creation is deterministic and behaves similarly across different runs.

decimation: int

Number of control action updates @ sim dt per policy dt.

For instance, if the simulation dt is 0.01s and the policy dt is 0.1s, then the decimation is 10. This means that the control action is updated every 10 simulation steps.

scene: InteractiveSceneCfg

Scene settings.

Please refer to the omni.isaac.lab.scene.InteractiveSceneCfg class for more details.

observations: object

Observation space settings.

Please refer to the omni.isaac.lab.managers.ObservationManager class for more details.

actions: object

Action space settings.

Please refer to the omni.isaac.lab.managers.ActionManager class for more details.

events: object

Event settings. Defaults to the basic configuration that resets the scene to its default state.

Please refer to the omni.isaac.lab.managers.EventManager class for more details.

rerender_on_reset: bool

Whether a render step is performed again after at least one environment has been reset. Defaults to False, which means no render step will be performed after reset.

• When this is False, data collected from sensors after performing reset will be stale and will not reflect the latest states in simulation caused by the reset.

• When this is True, an extra render step will be performed to update the sensor data to reflect the latest states from the reset. This comes at a cost of performance as an additional render step will be performed after each time an environment is reset.

terminations: object

Termination settings.

Please refer to the omni.isaac.lab.managers.TerminationManager class for more details.

curriculum: object | None

Curriculum settings. Defaults to None, in which case no curriculum is applied.

Please refer to the omni.isaac.lab.managers.CurriculumManager class for more details.

commands: object | None

Command settings. Defaults to None, in which case no commands are generated.

Please refer to the omni.isaac.lab.managers.CommandManager class for more details.

Direct RL Environment

class omni.isaac.lab.envs.DirectRLEnv

基类：Env

The superclass for the direct workflow to design environments.

This class implements the core functionality for reinforcement learning (RL) environments. It is designed to be used with any RL library. The class is designed to be used with vectorized environments, i.e., the environment is expected to be run in parallel with multiple sub-environments.

While the environment itself is implemented as a vectorized environment, we do not inherit from gym.vector.VectorEnv. This is mainly because the class adds various methods (for wait and asynchronous updates) which are not required. Additionally, each RL library typically has its own definition for a vectorized environment. Thus, to reduce complexity, we directly use the gym.Env over here and leave it up to library-defined wrappers to take care of wrapping this environment for their agents.

备注

For vectorized environments, it is recommended to only call the reset() method once before the first call to step(), i.e. after the environment is created. After that, the step() function handles the reset of terminated sub-environments. This is because the simulator does not support resetting individual sub-environments in a vectorized environment.

Attributes:

is_vector_env	Whether the environment is a vectorized environment.
metadata	Metadata for the environment.
num_envs	The number of instances of the environment that are running.
physics_dt	The physics time-step (in s).
step_dt	The environment stepping time-step (in s).
device	The device on which the environment is running.
max_episode_length_s	Maximum episode length in seconds.
max_episode_length	The maximum episode length in steps adjusted from s.
np_random	Returns the environment's internal _np_random that if not set will initialise with a random seed.
np_random_seed	Returns the environment's internal _np_random_seed that if not set will first initialise with a random int as seed.
unwrapped	Returns the base non-wrapped environment.

Methods:

__init__(cfg[, render_mode])	Initialize the environment.
reset([seed, options])	Resets all the environments and returns observations.
step(action)	Execute one time-step of the environment's dynamics.
seed([seed])	Set the seed for the environment.
render([recompute])	Run rendering without stepping through the physics.
close()	Cleanup for the environment.
set_debug_vis(debug_vis)	Toggles the environment debug visualization.
get_wrapper_attr(name)	Gets the attribute name from the environment.
has_wrapper_attr(name)	Checks if the attribute name exists in the environment.
set_wrapper_attr(name, value)	Sets the attribute name on the environment with value.

is_vector_env: ClassVar[bool] = True

Whether the environment is a vectorized environment.

metadata: ClassVar[dict[str, Any]] = {'isaac_sim_version': omni.isaac.version.get_version, 'render_modes': [None, 'human', 'rgb_array']}

Metadata for the environment.

__init__(cfg: DirectRLEnvCfg, render_mode: str | None = None, **kwargs)

Initialize the environment.

参数:

• cfg – The configuration object for the environment.

• render_mode – The render mode for the environment. Defaults to None, which is similar to "human".

抛出:

RuntimeError – If a simulation context already exists. The environment must always create one since it configures the simulation context and controls the simulation.

property num_envs: int

The number of instances of the environment that are running.

property physics_dt: float

The physics time-step (in s).

This is the lowest time-decimation at which the simulation is happening.

property step_dt: float

The environment stepping time-step (in s).

This is the time-step at which the environment steps forward.

property device

The device on which the environment is running.

property max_episode_length_s: float

Maximum episode length in seconds.

property max_episode_length

The maximum episode length in steps adjusted from s.

reset(seed: int | None = None, options: dict[str, Any] | None = None) → tuple[Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]], dict]

Resets all the environments and returns observations.

This function calls the _reset_idx() function to reset all the environments. However, certain operations, such as procedural terrain generation, that happened during initialization are not repeated.

参数:

• seed – The seed to use for randomization. Defaults to None, in which case the seed is not set.

• options –

  Additional information to specify how the environment is reset. Defaults to None.

  备注

  This argument is used for compatibility with Gymnasium environment definition.

返回:

A tuple containing the observations and extras.

step(action: torch.Tensor) → tuple[Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]], torch.Tensor, torch.Tensor, torch.Tensor, dict]

Execute one time-step of the environment’s dynamics.

The environment steps forward at a fixed time-step, while the physics simulation is decimated at a lower time-step. This is to ensure that the simulation is stable. These two time-steps can be configured independently using the DirectRLEnvCfg.decimation (number of simulation steps per environment step) and the DirectRLEnvCfg.sim.physics_dt (physics time-step). Based on these parameters, the environment time-step is computed as the product of the two.

This function performs the following steps:

1. Pre-process the actions before stepping through the physics.

2. Apply the actions to the simulator and step through the physics in a decimated manner.

3. Compute the reward and done signals.

4. Reset environments that have terminated or reached the maximum episode length.

5. Apply interval events if they are enabled.

6. Compute observations.

参数:

action – The actions to apply on the environment. Shape is (num_envs, action_dim).

返回:

A tuple containing the observations, rewards, resets (terminated and truncated) and extras.

static seed(seed: int = -1) → int

Set the seed for the environment.

参数:

seed – The seed for random generator. Defaults to -1.

返回:

The seed used for random generator.

render(recompute: bool = False) → np.ndarray | None

Run rendering without stepping through the physics.

By convention, if mode is:

• human: Render to the current display and return nothing. Usually for human consumption.

• rgb_array: Return an numpy.ndarray with shape (x, y, 3), representing RGB values for an x-by-y pixel image, suitable for turning into a video.

参数:

recompute – Whether to force a render even if the simulator has already rendered the scene. Defaults to False.

返回:

The rendered image as a numpy array if mode is “rgb_array”. Otherwise, returns None.

抛出:

• RuntimeError – If mode is set to “rgb_data” and simulation render mode does not support it. In this case, the simulation render mode must be set to RenderMode.PARTIAL_RENDERING or RenderMode.FULL_RENDERING.

• NotImplementedError – If an unsupported rendering mode is specified.

close()

Cleanup for the environment.

set_debug_vis(debug_vis: bool) → bool

Toggles the environment debug visualization.

参数:

debug_vis – Whether to visualize the environment debug visualization.

返回:

Whether the debug visualization was successfully set. False if the environment does not support debug visualization.

get_wrapper_attr(name: str) → Any

Gets the attribute name from the environment.

has_wrapper_attr(name: str) → bool

Checks if the attribute name exists in the environment.

property np_random: numpy.random.Generator

Returns the environment’s internal _np_random that if not set will initialise with a random seed.

返回:

Instances of np.random.Generator

property np_random_seed: int

Returns the environment’s internal _np_random_seed that if not set will first initialise with a random int as seed.

If np_random_seed was set directly instead of through reset() or set_np_random_through_seed(), the seed will take the value -1.

返回:

the seed of the current np_random or -1, if the seed of the rng is unknown

返回类型:

int

set_wrapper_attr(name: str, value: Any)

Sets the attribute name on the environment with value.

property unwrapped: Env[ObsType, ActType]

Returns the base non-wrapped environment.

返回:

The base non-wrapped gymnasium.Env instance

返回类型:

Env

class omni.isaac.lab.envs.DirectRLEnvCfg

基类：object

Configuration for an RL environment defined with the direct workflow.

Please refer to the omni.isaac.lab.envs.direct_rl_env.DirectRLEnv class for more details.

Attributes:

viewer	Viewer configuration.
sim	Physics simulation configuration.
seed	The seed for the random number generator.
decimation	Number of control action updates @ sim dt per policy dt.
is_finite_horizon	Whether the learning task is treated as a finite or infinite horizon problem for the agent.
episode_length_s	Duration of an episode (in seconds).
scene	Scene settings.
events	Event settings.
observation_space	Observation space definition.
num_observations	The dimension of the observation space from each environment instance.
state_space	State space definition.
num_states	The dimension of the state-space from each environment instance.
observation_noise_model	The noise model to apply to the computed observations from the environment.
action_space	Action space definition.
num_actions	The dimension of the action space for each environment.
action_noise_model	The noise model applied to the actions provided to the environment.
rerender_on_reset	Whether a render step is performed again after at least one environment has been reset.

Classes:

ui_window_class_type

BaseEnvWindow 的别名

viewer: ViewerCfg

Viewer configuration. Default is ViewerCfg().

sim: SimulationCfg

Physics simulation configuration. Default is SimulationCfg().

ui_window_class_type

BaseEnvWindow 的别名

seed: int | None

The seed for the random number generator. Defaults to None, in which case the seed is not set.

备注

The seed is set at the beginning of the environment initialization. This ensures that the environment creation is deterministic and behaves similarly across different runs.

decimation: int

Number of control action updates @ sim dt per policy dt.

For instance, if the simulation dt is 0.01s and the policy dt is 0.1s, then the decimation is 10. This means that the control action is updated every 10 simulation steps.

is_finite_horizon: bool

Whether the learning task is treated as a finite or infinite horizon problem for the agent. Defaults to False, which means the task is treated as an infinite horizon problem.

This flag handles the subtleties of finite and infinite horizon tasks:

• Finite horizon: no penalty or bootstrapping value is required by the the agent for running out of time. However, the environment still needs to terminate the episode after the time limit is reached.

• Infinite horizon: the agent needs to bootstrap the value of the state at the end of the episode. This is done by sending a time-limit (or truncated) done signal to the agent, which triggers this bootstrapping calculation.

If True, then the environment is treated as a finite horizon problem and no time-out (or truncated) done signal is sent to the agent. If False, then the environment is treated as an infinite horizon problem and a time-out (or truncated) done signal is sent to the agent.

备注

The base ManagerBasedRLEnv class does not use this flag directly. It is used by the environment wrappers to determine what type of done signal to send to the corresponding learning agent.

episode_length_s: float

Duration of an episode (in seconds).

Based on the decimation rate and physics time step, the episode length is calculated as:

episode_length_steps = ceil(episode_length_s / (decimation_rate * physics_time_step))

For example, if the decimation rate is 10, the physics time step is 0.01, and the episode length is 10 seconds, then the episode length in steps is 100.

scene: InteractiveSceneCfg

Scene settings.

Please refer to the omni.isaac.lab.scene.InteractiveSceneCfg class for more details.

events: object | None

Event settings. Defaults to None, in which case no events are applied through the event manager.

Please refer to the omni.isaac.lab.managers.EventManager class for more details.

observation_space: SpaceType

Observation space definition.

The space can be defined either using Gymnasium spaces (when a more detailed specification of the space is desired) or basic Python data types (for simplicity).

Gymnasium space	Python data type
Box	Integer or list of integers (e.g.: 7, [64, 64, 3])
Discrete	Single-element set (e.g.: {2})
MultiDiscrete	List of single-element sets (e.g.: [{2}, {5}])
Dict	Dictionary (e.g.: {"joints": 7, "rgb": [64, 64, 3], "gripper": {2}})
Tuple	Tuple (e.g.: (7, [64, 64, 3], {2}))

num_observations: int | None

The dimension of the observation space from each environment instance.

警告

This attribute is deprecated. Use observation_space instead.

state_space: SpaceType | None

State space definition.

This is useful for asymmetric actor-critic and defines the observation space for the critic.

The space can be defined either using Gymnasium spaces (when a more detailed specification of the space is desired) or basic Python data types (for simplicity).

Gymnasium space	Python data type
Box	Integer or list of integers (e.g.: 7, [64, 64, 3])
Discrete	Single-element set (e.g.: {2})
MultiDiscrete	List of single-element sets (e.g.: [{2}, {5}])
Dict	Dictionary (e.g.: {"joints": 7, "rgb": [64, 64, 3], "gripper": {2}})
Tuple	Tuple (e.g.: (7, [64, 64, 3], {2}))

num_states: int | None

The dimension of the state-space from each environment instance.

警告

This attribute is deprecated. Use state_space instead.

observation_noise_model: NoiseModelCfg | None

The noise model to apply to the computed observations from the environment. Default is None, which means no noise is added.

Please refer to the omni.isaac.lab.utils.noise.NoiseModel class for more details.

action_space: SpaceType

Action space definition.

The space can be defined either using Gymnasium spaces (when a more detailed specification of the space is desired) or basic Python data types (for simplicity).

Gymnasium space	Python data type
Box	Integer or list of integers (e.g.: 7, [64, 64, 3])
Discrete	Single-element set (e.g.: {2})
MultiDiscrete	List of single-element sets (e.g.: [{2}, {5}])
Dict	Dictionary (e.g.: {"joints": 7, "rgb": [64, 64, 3], "gripper": {2}})
Tuple	Tuple (e.g.: (7, [64, 64, 3], {2}))

num_actions: int | None

The dimension of the action space for each environment.

警告

This attribute is deprecated. Use action_space instead.

action_noise_model: NoiseModelCfg | None

The noise model applied to the actions provided to the environment. Default is None, which means no noise is added.

Please refer to the omni.isaac.lab.utils.noise.NoiseModel class for more details.

rerender_on_reset: bool

Whether a render step is performed again after at least one environment has been reset. Defaults to False, which means no render step will be performed after reset.

• When this is False, data collected from sensors after performing reset will be stale and will not reflect the latest states in simulation caused by the reset.

• When this is True, an extra render step will be performed to update the sensor data to reflect the latest states from the reset. This comes at a cost of performance as an additional render step will be performed after each time an environment is reset.

Direct Multi-Agent RL Environment

class omni.isaac.lab.envs.DirectMARLEnv

基类：object

The superclass for the direct workflow to design multi-agent environments.

This class implements the core functionality for multi-agent reinforcement learning (MARL) environments. It is designed to be used with any RL library. The class is designed to be used with vectorized environments, i.e., the environment is expected to be run in parallel with multiple sub-environments.

The design of this class is based on the PettingZoo Parallel API. While the environment itself is implemented as a vectorized environment, we do not inherit from pettingzoo.ParallelEnv or gym.vector.VectorEnv. This is mainly because the class adds various attributes and methods that are inconsistent with them.

备注

For vectorized environments, it is recommended to only call the reset() method once before the first call to step(), i.e. after the environment is created. After that, the step() function handles the reset of terminated sub-environments. This is because the simulator does not support resetting individual sub-environments in a vectorized environment.

Attributes:

metadata	Metadata for the environment.
num_envs	The number of instances of the environment that are running.
num_agents	Number of current agents.
max_num_agents	Number of all possible agents the environment can generate.
unwrapped	Get the unwrapped environment underneath all the layers of wrappers.
physics_dt	The physics time-step (in s).
step_dt	The environment stepping time-step (in s).
device	The device on which the environment is running.
max_episode_length_s	Maximum episode length in seconds.
max_episode_length	The maximum episode length in steps adjusted from s.

Methods:

__init__(cfg[, render_mode])	Initialize the environment.
observation_space(agent)	Get the observation space for the specified agent.
action_space(agent)	Get the action space for the specified agent.
reset([seed, options])	Resets all the environments and returns observations.
step(actions)	Execute one time-step of the environment's dynamics.
state()	Returns the state for the environment.
seed([seed])	Set the seed for the environment.
render([recompute])	Run rendering without stepping through the physics.
close()	Cleanup for the environment.
set_debug_vis(debug_vis)	Toggles the environment debug visualization.

metadata: ClassVar[dict[str, Any]] = {'isaac_sim_version': omni.isaac.version.get_version, 'render_modes': [None, 'human', 'rgb_array']}

Metadata for the environment.

__init__(cfg: DirectMARLEnvCfg, render_mode: str | None = None, **kwargs)

Initialize the environment.

参数:

• cfg – The configuration object for the environment.

• render_mode – The render mode for the environment. Defaults to None, which is similar to "human".

抛出:

RuntimeError – If a simulation context already exists. The environment must always create one since it configures the simulation context and controls the simulation.

property num_envs: int

The number of instances of the environment that are running.

property num_agents: int

Number of current agents.

The number of current agents may change as the environment progresses (e.g.: agents can be added or removed).

property max_num_agents: int

Number of all possible agents the environment can generate.

This value remains constant as the environment progresses.

property unwrapped: DirectMARLEnv

Get the unwrapped environment underneath all the layers of wrappers.

property physics_dt: float

The physics time-step (in s).

This is the lowest time-decimation at which the simulation is happening.

property step_dt: float

The environment stepping time-step (in s).

This is the time-step at which the environment steps forward.

property device

The device on which the environment is running.

property max_episode_length_s: float

Maximum episode length in seconds.

property max_episode_length

The maximum episode length in steps adjusted from s.

observation_space(agent: AgentID) → Space

Get the observation space for the specified agent.

返回:

The agent’s observation space.

action_space(agent: AgentID) → Space

Get the action space for the specified agent.

返回:

The agent’s action space.

reset(seed: int | None = None, options: dict[str, Any] | None = None) → tuple[dict[AgentID, ObsType], dict[AgentID, dict]]

Resets all the environments and returns observations.

参数:

• seed – The seed to use for randomization. Defaults to None, in which case the seed is not set.

• options –

  Additional information to specify how the environment is reset. Defaults to None.

  备注

  This argument is used for compatibility with Gymnasium environment definition.

返回:

A tuple containing the observations and extras (keyed by the agent ID).

step(actions: dict[AgentID, ActionType]) → tuple[Dict[AgentID, ObsType], Dict[AgentID, torch.Tensor], Dict[AgentID, torch.Tensor], Dict[AgentID, torch.Tensor], Dict[AgentID, dict]]

Execute one time-step of the environment’s dynamics.

The environment steps forward at a fixed time-step, while the physics simulation is decimated at a lower time-step. This is to ensure that the simulation is stable. These two time-steps can be configured independently using the DirectMARLEnvCfg.decimation (number of simulation steps per environment step) and the DirectMARLEnvCfg.sim.physics_dt (physics time-step). Based on these parameters, the environment time-step is computed as the product of the two.

This function performs the following steps:

1. Pre-process the actions before stepping through the physics.

2. Apply the actions to the simulator and step through the physics in a decimated manner.

3. Compute the reward and done signals.

4. Reset environments that have terminated or reached the maximum episode length.

5. Apply interval events if they are enabled.

6. Compute observations.

参数:

actions – The actions to apply on the environment (keyed by the agent ID). Shape of individual tensors is (num_envs, action_dim).

返回:

A tuple containing the observations, rewards, resets (terminated and truncated) and extras (keyed by the agent ID).

state() → StateType | None

Returns the state for the environment.

The state-space is used for centralized training or asymmetric actor-critic architectures. It is configured using the DirectMARLEnvCfg.state_space parameter.

返回:

The states for the environment, or None if DirectMARLEnvCfg.state_space parameter is zero.

static seed(seed: int = -1) → int

Set the seed for the environment.

参数:

seed – The seed for random generator. Defaults to -1.

返回:

The seed used for random generator.

render(recompute: bool = False) → np.ndarray | None

Run rendering without stepping through the physics.

By convention, if mode is:

• human: Render to the current display and return nothing. Usually for human consumption.

• rgb_array: Return an numpy.ndarray with shape (x, y, 3), representing RGB values for an x-by-y pixel image, suitable for turning into a video.

参数:

recompute – Whether to force a render even if the simulator has already rendered the scene. Defaults to False.

返回:

The rendered image as a numpy array if mode is “rgb_array”. Otherwise, returns None.

抛出:

• RuntimeError – If mode is set to “rgb_data” and simulation render mode does not support it. In this case, the simulation render mode must be set to RenderMode.PARTIAL_RENDERING or RenderMode.FULL_RENDERING.

• NotImplementedError – If an unsupported rendering mode is specified.

close()

Cleanup for the environment.

set_debug_vis(debug_vis: bool) → bool

Toggles the environment debug visualization.

参数:

debug_vis – Whether to visualize the environment debug visualization.

返回:

Whether the debug visualization was successfully set. False if the environment does not support debug visualization.

class omni.isaac.lab.envs.DirectMARLEnvCfg

基类：object

Configuration for a MARL environment defined with the direct workflow.

Please refer to the omni.isaac.lab.envs.direct_marl_env.DirectMARLEnv class for more details.

Attributes:

viewer	Viewer configuration.
sim	Physics simulation configuration.
seed	The seed for the random number generator.
decimation	Number of control action updates @ sim dt per policy dt.
is_finite_horizon	Whether the learning task is treated as a finite or infinite horizon problem for the agent.
episode_length_s	Duration of an episode (in seconds).
scene	Scene settings.
events	Event settings.
observation_spaces	Observation space definition for each agent.
num_observations	The dimension of the observation space for each agent.
state_space	State space definition.
num_states	The dimension of the state space from each environment instance.
observation_noise_model	The noise model to apply to the computed observations from the environment.
action_spaces	Action space definition for each agent.
num_actions	The dimension of the action space for each agent.
action_noise_model	The noise model applied to the actions provided to the environment.
possible_agents	A list of all possible agents the environment could generate.

Classes:

ui_window_class_type

BaseEnvWindow 的别名

viewer: ViewerCfg

Viewer configuration. Default is ViewerCfg().

sim: SimulationCfg

Physics simulation configuration. Default is SimulationCfg().

ui_window_class_type

BaseEnvWindow 的别名

seed: int | None

The seed for the random number generator. Defaults to None, in which case the seed is not set.

备注

The seed is set at the beginning of the environment initialization. This ensures that the environment creation is deterministic and behaves similarly across different runs.

decimation: int

Number of control action updates @ sim dt per policy dt.

For instance, if the simulation dt is 0.01s and the policy dt is 0.1s, then the decimation is 10. This means that the control action is updated every 10 simulation steps.

is_finite_horizon: bool

Whether the learning task is treated as a finite or infinite horizon problem for the agent. Defaults to False, which means the task is treated as an infinite horizon problem.

This flag handles the subtleties of finite and infinite horizon tasks:

• Finite horizon: no penalty or bootstrapping value is required by the the agent for running out of time. However, the environment still needs to terminate the episode after the time limit is reached.

• Infinite horizon: the agent needs to bootstrap the value of the state at the end of the episode. This is done by sending a time-limit (or truncated) done signal to the agent, which triggers this bootstrapping calculation.

If True, then the environment is treated as a finite horizon problem and no time-out (or truncated) done signal is sent to the agent. If False, then the environment is treated as an infinite horizon problem and a time-out (or truncated) done signal is sent to the agent.

备注

The base ManagerBasedRLEnv class does not use this flag directly. It is used by the environment wrappers to determine what type of done signal to send to the corresponding learning agent.

episode_length_s: float

Duration of an episode (in seconds).

Based on the decimation rate and physics time step, the episode length is calculated as:

episode_length_steps = ceil(episode_length_s / (decimation_rate * physics_time_step))

For example, if the decimation rate is 10, the physics time step is 0.01, and the episode length is 10 seconds, then the episode length in steps is 100.

scene: InteractiveSceneCfg

Scene settings.

Please refer to the omni.isaac.lab.scene.InteractiveSceneCfg class for more details.

events: object

Event settings. Defaults to None, in which case no events are applied through the event manager.

Please refer to the omni.isaac.lab.managers.EventManager class for more details.

observation_spaces: dict[AgentID, SpaceType]

Observation space definition for each agent.

The space can be defined either using Gymnasium spaces (when a more detailed specification of the space is desired) or basic Python data types (for simplicity).

Gymnasium space	Python data type
Box	Integer or list of integers (e.g.: 7, [64, 64, 3])
Discrete	Single-element set (e.g.: {2})
MultiDiscrete	List of single-element sets (e.g.: [{2}, {5}])
Dict	Dictionary (e.g.: {"joints": 7, "rgb": [64, 64, 3], "gripper": {2}})
Tuple	Tuple (e.g.: (7, [64, 64, 3], {2}))

num_observations: dict[AgentID, int] | None

The dimension of the observation space for each agent.

警告

This attribute is deprecated. Use observation_spaces instead.

state_space: SpaceType

State space definition.

The following values are supported:

• -1: All the observations from the different agents are automatically concatenated.

• 0: No state-space will be constructed (state_space is None). This is useful to save computational resources when the algorithm to be trained does not need it.

• greater than 0: Custom state-space dimension to be provided by the task implementation.

The space can be defined either using Gymnasium spaces (when a more detailed specification of the space is desired) or basic Python data types (for simplicity).

Gymnasium space	Python data type
Box	Integer or list of integers (e.g.: 7, [64, 64, 3])
Discrete	Single-element set (e.g.: {2})
MultiDiscrete	List of single-element sets (e.g.: [{2}, {5}])
Dict	Dictionary (e.g.: {"joints": 7, "rgb": [64, 64, 3], "gripper": {2}})
Tuple	Tuple (e.g.: (7, [64, 64, 3], {2}))

num_states: int | None

The dimension of the state space from each environment instance.

警告

This attribute is deprecated. Use state_space instead.

observation_noise_model: dict[AgentID, omni.isaac.lab.utils.noise.noise_cfg.NoiseModelCfg | None] | None

The noise model to apply to the computed observations from the environment. Default is None, which means no noise is added.

Please refer to the omni.isaac.lab.utils.noise.NoiseModel class for more details.

action_spaces: dict[AgentID, SpaceType]

Action space definition for each agent.

The space can be defined either using Gymnasium spaces (when a more detailed specification of the space is desired) or basic Python data types (for simplicity).

Gymnasium space	Python data type
Box	Integer or list of integers (e.g.: 7, [64, 64, 3])
Discrete	Single-element set (e.g.: {2})
MultiDiscrete	List of single-element sets (e.g.: [{2}, {5}])
Dict	Dictionary (e.g.: {"joints": 7, "rgb": [64, 64, 3], "gripper": {2}})
Tuple	Tuple (e.g.: (7, [64, 64, 3], {2}))

num_actions: dict[AgentID, int] | None

The dimension of the action space for each agent.

警告

This attribute is deprecated. Use action_spaces instead.

action_noise_model: dict[AgentID, omni.isaac.lab.utils.noise.noise_cfg.NoiseModelCfg | None] | None

The noise model applied to the actions provided to the environment. Default is None, which means no noise is added.

Please refer to the omni.isaac.lab.utils.noise.NoiseModel class for more details.

possible_agents: list[AgentID]

A list of all possible agents the environment could generate.

The contents of the list cannot be modified during the entire training process.

Common

class omni.isaac.lab.envs.ViewerCfg

Configuration of the scene viewport camera.

Attributes:

eye	Initial camera position (in m).
lookat	Initial camera target position (in m).
cam_prim_path	The camera prim path to record images from.
resolution	The resolution (width, height) of the camera specified using cam_prim_path.
origin_type	The frame in which the camera position (eye) and target (lookat) are defined in.
env_index	The environment index for frame origin.
asset_name	The asset name in the interactive scene for the frame origin.

eye: tuple[float, float, float]

Initial camera position (in m). Default is (7.5, 7.5, 7.5).

lookat: tuple[float, float, float]

Initial camera target position (in m). Default is (0.0, 0.0, 0.0).

cam_prim_path: str

The camera prim path to record images from. Default is “/OmniverseKit_Persp”, which is the default camera in the viewport.

resolution: tuple[int, int]

The resolution (width, height) of the camera specified using cam_prim_path. Default is (1280, 720).

origin_type: Literal['world', 'env', 'asset_root']

The frame in which the camera position (eye) and target (lookat) are defined in. Default is “world”.

Available options are:

• "world": The origin of the world.

• "env": The origin of the environment defined by env_index.

• "asset_root": The center of the asset defined by asset_name in environment env_index.

env_index: int

The environment index for frame origin. Default is 0.

This quantity is only effective if origin is set to “env” or “asset_root”.

asset_name: str | None

The asset name in the interactive scene for the frame origin. Default is None.

This quantity is only effective if origin is set to “asset_root”.