GenesisEnv#

class genesis_forge.GenesisEnv(num_envs: int = 1, dt: float = 0.01, max_episode_length_sec: int | None = 10, max_episode_random_scaling: float = 0.0, extras_logging_key: str = 'episode')[source]#

Bases: object

Base environment class for your simulated robot environment.

Parameters:

num_envs – Number of parallel environments.
dt – Simulation time step.
max_episode_length_sec – Maximum episode length in seconds.
max_episode_random_scaling – Scale the maximum episode length by this amount (+/-) so that not all environments reset at the same time.
extras_logging_key – The key used, in info/extras dict, which is returned by step and reset functions, to send data to tensorboard by the RL agent.

Example:

class MyEnv(GenesisEnv):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)

        # ...Define scene here...
        self.scene = gs.Scene()
        self.terrain = self.scene.add_entity(gs.morphs.Plane())
        self.robot = self.scene.add_entity( ... )

    def step(self, actions: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, dict[str, Any]]:
        # ...step logic here...
        return obs, rewards, terminations, truncations, info

    def reset(self, envs_idx: list[int] = None) -> tuple[torch.Tensor, dict[str, Any]]:
        # ...reset logic here...
        return obs, info

    def get_observations(self) -> torch.Tensor:
        # ...define current observations here...
        return obs

build() → None[source]#: Builds the environment before the first step. The Genesis scene and all the scene entities must be added before calling this method.

close()[source]#: Close the environment.

get_observations() → torch.Tensor[source]#

Returns the current observations for each environment. Override this method to return the observations for your environment.

Example:

def get_observations(self) -> torch.Tensor:
    return torch.cat(
    [
        self.base_ang_vel * self.obs_scales["ang_vel"],  # 3
        self.projected_gravity,  # 3
        self.commands * self.commands_scale,  # 3
        (self.dof_pos - self.default_dof_pos) * self.obs_scales["dof_pos"],  # 12
        self.dof_vel * self.obs_scales["dof_vel"],  # 12
        self.actions,  # 12
    ],
    axis=-1,
)

reset(envs_idx: list[int] = None) → tuple[torch.Tensor, dict[str, Any]][source]#

Reset one or more environments. Each of the registered managers will also be reset for those environments.

Parameters:: env_ids – The environment ids to reset. If None, all environments are reset.
Returns:: A batch of observations and info from the vectorized environment.

set_max_episode_length(max_episode_length_sec: int) → int[source]#

Set or change the maximum episode length.

Parameters:: max_episode_length_sec – The maximum episode length in seconds.
Returns:: The maximum episode length in steps.

step(actions: torch.Tensor) → tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, dict[str, Any]][source]#

Performs a step in all environments with the given actions.

Parameters:: actions – Batch of actions for each environment with the action_space shape.
Returns:: Batch of (observations, rewards, terminations, truncations, info/extras)

action_space: spaces.Space | None = None#

property actions: torch.Tensor#: The actions for each environment for this step. If you’re using an action manager, these are the actions prior to being handled by the action manager.

can_be_wrapped: bool = True#

property extras: dict#: The extras/infos dictionary reset at the start of every step, and contains additional data about the environment during that step.

property last_actions: torch.Tensor#: The actions for for the previous step.

property max_episode_length_sec: int | None#: The max episode length, in seconds, for each environment.

property max_episode_length_steps: int | None#: The max episode length, in steps, for each environment. If episode randomization scaling is enabled, this will be the base max episode length before scaling.

property num_actions: int#: The number of actions for each environment.

property num_observations: int#: The number of observations for each environment.

observation_space: spaces.Space | None = None#

property unwrapped#: Returns this environment, not a wrapped version of it.

GenesisEnv#

This Page