Rsl_RL#

class genesis_forge.wrappers.RslRlWrapper(env: GenesisEnv, cfg: dict | object = {})[source]#

Bases: Wrapper

A wrapper that makes your genesis forge environment compatible with the rsl_rl training framework.

IMPORTANT: This should be the last wrapper, as the change in the step and get_observations methods might break other wrappers.

What it does:

Combines the terminated and truncated tensors into a single tensor (i.e. terminated | truncated).
Add the truncated tensor to the extras dictionary as “time_outs”.
Returns observations and extras from the get_observations method.

Parameters:

env – The environment to wrap.
cfg – The configuration for the wrapper that will be passed to the neptune or wandb logger

Initialize the logging wrapper with the function to use for data logging.

build() → None#: Builds the scene and other supporting components necessary for the training environment. This assumes that the scene has already been constructed and assigned to the <env>.scene attribute.

close()#: Closes the wrapper and env.

get_observations()[source]#: Returns observations as well as an extras dictionary with the observations added to the extras[“observations”][“critic”] key.

reset()[source]#: Converts observations into a TensorDict for rsl_rl 3.0+

step(actions: torch.Tensor) → tuple[torch.Tensor, torch.Tensor, torch.Tensor, dict[str, Any]][source]#: Returns a single “dones” tensor, instead of the terminated and truncated tensors (via terminated | truncated). Add the truncated tensor to the extras dictionary as “time_outs”.

property action_space: gymnasium.spaces#: The action space of the environment.

can_be_wrapped: bool = False#

property device: str#

property dt: float#: The time step of the environment.

env: GenesisEnv = None#

property extras: dict#: The extras/infos dictionary that should be returned by the step and reset functions. This dictionary will be cleared at the start of every step.

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

property num_envs: int#: The number of parallel environments.

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

property observation_space: gymnasium.spaces#: The observation space of the environment.

property robot: Any#: Get the environment robot.

property scene: genesis.Scene#: Get the environment scene.

property unwrapped: GenesisEnv#

Returns the base environment of the wrapper.

This will be the bare ManagedEnvironment or GenesisEnv environment, underneath all layers of wrappers.