src.environment.parallelenv.worker.raysubproc

Module Contents

Classes

RaySubprocEnvWorker

Nested use Subprocessing parallel under ray parallel

API

class src.environment.parallelenv.worker.raysubproc.RaySubprocEnvWorker(env_fns: Callable[[], gym.Env], worker_fn, num_cpu_per_worker=1, num_gpu_per_worker=0, no_warning=False)[source]

Bases: src.environment.parallelenv.worker.base.EnvWorker

Nested use Subprocessing parallel under ray parallel

Initialization

num_cpu_per_worker[source]

1

num_gpu_per_worker[source]

0

get_env_attr(key: str, id=None) → Any[source]
set_env_attr(key: str, value: Any, id=None) → None[source]
send_reset(id=None) → Any[source]
ray_reset(envs, id, no_warning)[source]
customized_method(func: str, data=None, id=None) → Any[source]
ray_customized(envs, func, data, id, no_warning)[source]
static wait(workers: List[src.environment.parallelenv.worker.raysubproc.RaySubprocEnvWorker], wait_num: int, timeout: Optional[float] = None) → List[src.environment.parallelenv.worker.raysubproc.RaySubprocEnvWorker][source]
send(action: Optional[numpy.ndarray], id: Optional[numpy.ndarray] = None) → None[source]
ray_step(envs, action, id, no_warning)[source]
recv() → Union[Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray], numpy.ndarray][source]
seed(seed: Optional[int] = None) → List[int][source]
render(**kwargs: Any) → Any[source]
close_env() → None[source]