Command Utils

Helpers for scripts like run_atari.py.

stable_baselines.common.cmd_util.arg_parser()[source]

Create an empty argparse.ArgumentParser.

Returns:(ArgumentParser)
stable_baselines.common.cmd_util.atari_arg_parser()[source]

Create an argparse.ArgumentParser for run_atari.py.

Returns:(ArgumentParser) parser {‘–env’: ‘BreakoutNoFrameskip-v4’, ‘–seed’: 0, ‘–num-timesteps’: int(1e7)}
stable_baselines.common.cmd_util.make_atari_env(env_id, num_env, seed, wrapper_kwargs=None, start_index=0, allow_early_resets=True, start_method=None)[source]

Create a wrapped, monitored SubprocVecEnv for Atari.

Parameters:
  • env_id – (str) the environment ID
  • num_env – (int) the number of environment you wish to have in subprocesses
  • seed – (int) the inital seed for RNG
  • wrapper_kwargs – (dict) the parameters for wrap_deepmind function
  • start_index – (int) start rank index
  • allow_early_resets – (bool) allows early reset of the environment
  • start_method – (str) method used to start the subprocesses. See SubprocVecEnv doc for more information
Returns:

(Gym Environment) The atari environment

stable_baselines.common.cmd_util.make_mujoco_env(env_id, seed, allow_early_resets=True)[source]

Create a wrapped, monitored gym.Env for MuJoCo.

Parameters:
  • env_id – (str) the environment ID
  • seed – (int) the inital seed for RNG
  • allow_early_resets – (bool) allows early reset of the environment
Returns:

(Gym Environment) The mujoco environment

stable_baselines.common.cmd_util.make_robotics_env(env_id, seed, rank=0, allow_early_resets=True)[source]

Create a wrapped, monitored gym.Env for MuJoCo.

Parameters:
  • env_id – (str) the environment ID
  • seed – (int) the inital seed for RNG
  • rank – (int) the rank of the environment (for logging)
  • allow_early_resets – (bool) allows early reset of the environment
Returns:

(Gym Environment) The robotic environment

stable_baselines.common.cmd_util.mujoco_arg_parser()[source]

Create an argparse.ArgumentParser for run_mujoco.py.

Returns:(ArgumentParser) parser {‘–env’: ‘Reacher-v2’, ‘–seed’: 0, ‘–num-timesteps’: int(1e6), ‘–play’: False}
stable_baselines.common.cmd_util.robotics_arg_parser()[source]

Create an argparse.ArgumentParser for run_mujoco.py.

Returns:(ArgumentParser) parser {‘–env’: ‘FetchReach-v0’, ‘–seed’: 0, ‘–num-timesteps’: int(1e6)}