pytorchrl.agent.env.openai_baselines_dependencies package

Subpackages

• pytorchrl.agent.env.openai_baselines_dependencies.vec_env package
  • Submodules
  • pytorchrl.agent.env.openai_baselines_dependencies.vec_env.dummy_vec_env module
  • pytorchrl.agent.env.openai_baselines_dependencies.vec_env.subproc_vec_env module
  • pytorchrl.agent.env.openai_baselines_dependencies.vec_env.util module
  • pytorchrl.agent.env.openai_baselines_dependencies.vec_env.vec_env module
  • Module contents

Submodules

pytorchrl.agent.env.openai_baselines_dependencies.Monitor module

exception pytorchrl.agent.env.openai_baselines_dependencies.Monitor.LoadMonitorResultsError

Bases: Exception

class pytorchrl.agent.env.openai_baselines_dependencies.Monitor.Monitor(env, filename, allow_early_resets=False, reset_keywords=(), info_keywords=())

Bases: gym.core.Wrapper

EXT = 'monitor.csv'

close()

Override close in your subclass to perform any necessary cleanup.

Environments will automatically close() themselves when garbage collected or when the program exits.

f = None

get_episode_lengths()

get_episode_rewards()

get_episode_times()

get_total_steps()

reset(**kwargs)

Resets the environment to an initial state and returns an initial observation.

Note that this function should not reset the environment’s random number generator(s); random variables in the environment’s state should be sampled independently between multiple calls to reset(). In other words, each call of reset() should yield an environment suitable for a new episode, independent of previous episodes.

Returns

the initial observation.

Return type

observation (object)

reset_state()

step(action)

Run one timestep of the environment’s dynamics. When end of episode is reached, you are responsible for calling reset() to reset this environment’s state.

Accepts an action and returns a tuple (observation, reward, done, info).

Parameters

action (object) – an action provided by the agent

Returns

agent’s observation of the current environment reward (float) : amount of reward returned after previous action done (bool): whether the episode has ended, in which case further step() calls will return undefined results info (dict): contains auxiliary diagnostic information (helpful for debugging, and sometimes learning)

Return type

observation (object)

update(ob, rew, done, info)

class pytorchrl.agent.env.openai_baselines_dependencies.Monitor.ResultsWriter(filename, header='', extra_keys=())

Bases: object

write_row(epinfo)

pytorchrl.agent.env.openai_baselines_dependencies.Monitor.get_monitor_files(dir)

pytorchrl.agent.env.openai_baselines_dependencies.Monitor.load_results(dir)

pytorchrl.agent.env.openai_baselines_dependencies.load_baselines_results module

pytorchrl.agent.env.openai_baselines_dependencies.load_baselines_results.load_baselines_results(dir)

Module contents