Language Language English 简体中文

unilab.algos.torch.rsl_rl_ppo.FinalObservationAwarePPO

class unilab.algos.torch.rsl_rl_ppo.FinalObservationAwarePPO

Bases: PPO

PPO variant that bootstraps time limits from env final_observation.

Parameters:

• args (Any)

• enable_compile (bool)

• kwargs (Any)

Methods

__init__(*args[, enable_compile])
process_env_step(obs, rewards, dones, extras)
update()

Attributes

learning_rate

learning_rate: float

__init__(*args, enable_compile=False, **kwargs)

Parameters:

• args (Any)

• enable_compile (bool)

• kwargs (Any)

update()

Return type:

dict[str, float]

process_env_step(obs, rewards, dones, extras)

Parameters:

• obs (TensorDict)

• rewards (Tensor)

• dones (Tensor)

• extras (dict[str, Tensor | TensorDict])

Return type:

None

__call__(*args, **kwargs)

Call self as a function.

Parameters:

• args (Any)

• kwargs (Any)

Return type:

Any

__getitem__(key)

Parameters:

key (Any)

Return type:

_MockObject

__len__()

Return type:

int

static __new__(cls, *args, **kwargs)

Parameters:

• args (Any)

• kwargs (Any)

Return type:

Any