pytorchrl.envs.mujoco package

Submodules

pytorchrl.envs.mujoco.mujoco_env_factory module

pytorchrl.envs.mujoco.mujoco_env_factory.mujoco_test_env_factory(env_id, index_col_worker, index_grad_worker, index_env=0, seed=0, frame_skip=0, frame_stack=1, reward_delay=1)

Create test MuJoCo environment.

Parameters

• env_id (str) – Environment name.

• index_col_worker (int) – Index of the collection worker running this environment.

• index_grad_worker (int) – Index of the gradient worker running the collection worker running this environment.

• index_env (int) – Index of this environment withing the vector of environments.

• seed (int) – Environment random seed.

• frame_skip (int) – Return only every frame_skip-th observation.

• frame_stack (int) – Observations composed of last frame_stack frames stacked.

• reward_delay (int) – Only return accumulated reward every reward_delay steps to simulate sparse reward environment.

Returns

env – Test environment.

Return type

gym.Env

pytorchrl.envs.mujoco.mujoco_env_factory.mujoco_train_env_factory(env_id, index_col_worker, index_grad_worker, index_env=0, seed=0, frame_skip=0, frame_stack=1, reward_delay=1)

Create train MuJoCo environment.

Parameters

• env_id (str) – Environment name.

• index_col_worker (int) – Index of the collection worker running this environment.

• index_grad_worker (int) – Index of the gradient worker running the collection worker running this environment.

• index_env (int) – Index of this environment withing the vector of environments.

• seed (int) – Environment random seed.

• frame_skip (int) – Return only every frame_skip-th observation.

• frame_stack (int) – Observations composed of last frame_stack frames stacked.

• reward_delay (int) – Only return accumulated reward every reward_delay steps to simulate sparse reward environment.

Returns

env – Train environment.

Return type

gym.Env

Module contents