Module TeachMyAgent.students.openai_baselines.common.wrappers

Classes

class ClipActionsWrapper (env: gym.core.Env)

Wraps an environment to allow a modular transformation of the :meth:step and :meth:reset methods.

This class is the base class for all wrappers. The subclass could override some methods to change the behavior of the original environment without touching the original code.

Note

Don't forget to call super().__init__(env) if the subclass overrides :meth:__init__.

Wraps an environment to allow a modular transformation of the :meth:step and :meth:reset methods.

Args

env

The environment to wrap

Expand source code

class ClipActionsWrapper(gym.Wrapper):
    def step(self, action):
        import numpy as np
        action = np.nan_to_num(action)
        action = np.clip(action, self.action_space.low, self.action_space.high)
        return self.env.step(action)

    def reset(self, **kwargs):
        return self.env.reset(**kwargs)

Ancestors

• gym.core.Wrapper
• gym.core.Env
• typing.Generic

Instance variables

var action_space : gym.spaces.space.Space[~ActType]

Returns the action space of the environment.

Expand source code

@property
def action_space(self) -> spaces.Space[ActType]:
    """Returns the action space of the environment."""
    if self._action_space is None:
        return self.env.action_space
    return self._action_space

var metadata : dict

Returns the environment metadata.

Expand source code

@property
def metadata(self) -> dict:
    """Returns the environment metadata."""
    if self._metadata is None:
        return self.env.metadata
    return self._metadata

var observation_space : gym.spaces.space.Space

Returns the observation space of the environment.

Expand source code

@property
def observation_space(self) -> spaces.Space:
    """Returns the observation space of the environment."""
    if self._observation_space is None:
        return self.env.observation_space
    return self._observation_space

var render_mode : Union[str, NoneType]

Returns the environment render_mode.

Expand source code

@property
def render_mode(self) -> Optional[str]:
    """Returns the environment render_mode."""
    return self.env.render_mode

var spec

Returns the environment specification.

Expand source code

@property
def spec(self):
    """Returns the environment specification."""
    return self.env.spec

Methods

def reset(self, **kwargs)

Resets the environment with kwargs.

Expand source code

def reset(self, **kwargs):
    return self.env.reset(**kwargs)

def step(self, action)

Steps through the environment with action.

Expand source code

def step(self, action):
    import numpy as np
    action = np.nan_to_num(action)
    action = np.clip(action, self.action_space.low, self.action_space.high)
    return self.env.step(action)

class TimeLimit (env, max_episode_steps=None)

Wraps an environment to allow a modular transformation of the :meth:step and :meth:reset methods.

This class is the base class for all wrappers. The subclass could override some methods to change the behavior of the original environment without touching the original code.

Note

Don't forget to call super().__init__(env) if the subclass overrides :meth:__init__.

Wraps an environment to allow a modular transformation of the :meth:step and :meth:reset methods.

Args

env

The environment to wrap

Expand source code

class TimeLimit(gym.Wrapper):
    def __init__(self, env, max_episode_steps=None):
        super(TimeLimit, self).__init__(env)
        self._max_episode_steps = max_episode_steps
        self._elapsed_steps = 0

    def step(self, ac):
        observation, reward, done, info = self.env.step(ac)
        self._elapsed_steps += 1
        if self._elapsed_steps >= self._max_episode_steps:
            done = True
            info['TimeLimit.truncated'] = True
        return observation, reward, done, info

    def reset(self, **kwargs):
        self._elapsed_steps = 0
        return self.env.reset(**kwargs)

Ancestors

• gym.core.Wrapper
• gym.core.Env
• typing.Generic

Instance variables

var action_space : gym.spaces.space.Space[~ActType]

Returns the action space of the environment.

Expand source code

@property
def action_space(self) -> spaces.Space[ActType]:
    """Returns the action space of the environment."""
    if self._action_space is None:
        return self.env.action_space
    return self._action_space

var metadata : dict

Returns the environment metadata.

Expand source code

@property
def metadata(self) -> dict:
    """Returns the environment metadata."""
    if self._metadata is None:
        return self.env.metadata
    return self._metadata

var observation_space : gym.spaces.space.Space

Returns the observation space of the environment.

Expand source code

@property
def observation_space(self) -> spaces.Space:
    """Returns the observation space of the environment."""
    if self._observation_space is None:
        return self.env.observation_space
    return self._observation_space

var render_mode : Union[str, NoneType]

Returns the environment render_mode.

Expand source code

@property
def render_mode(self) -> Optional[str]:
    """Returns the environment render_mode."""
    return self.env.render_mode

var spec

Returns the environment specification.

Expand source code

@property
def spec(self):
    """Returns the environment specification."""
    return self.env.spec

Methods

def reset(self, **kwargs)

Resets the environment with kwargs.

Expand source code

def reset(self, **kwargs):
    self._elapsed_steps = 0
    return self.env.reset(**kwargs)

def step(self, ac)

Steps through the environment with action.

Expand source code

def step(self, ac):
    observation, reward, done, info = self.env.step(ac)
    self._elapsed_steps += 1
    if self._elapsed_steps >= self._max_episode_steps:
        done = True
        info['TimeLimit.truncated'] = True
    return observation, reward, done, info