garage.envs.wrappers package

gym.Env wrappers.

Used to transform an environment in a modular way. It is also possible to apply multiple wrappers at the same time.

Example

StackFrames(GrayScale(gym.make(‘env’)))

class AtariEnv(env)[source]

Bases: gym.core.Wrapper

Atari environment wrapper for gym.Env.

This wrapper convert the observations returned from baselines wrapped environment, which is a LazyFrames object into numpy arrays.

Parameters:env (gym.Env) – The environment to be wrapped.
reset(**kwargs)[source]

gym.Env reset function.

step(action)[source]

gym.Env step function.

class ClipReward(env)[source]

Bases: gym.core.Wrapper

Clip the reward by its sign.

reset()[source]

gym.Env reset.

step(ac)[source]

gym.Env step function.

class EpisodicLife(env)[source]

Bases: gym.core.Wrapper

Episodic life wrapper for gym.Env.

This wrapper makes episode end when a life is lost, but only reset when all lives are lost.

Parameters:env – The environment to be wrapped.
reset(**kwargs)[source]

gym.Env reset function.

Reset only when lives are lost.

step(action)[source]

gym.Env step function.

class FireReset(env)[source]

Bases: gym.core.Wrapper

Fire reset wrapper for gym.Env.

Take action “fire” on reset.

Parameters:env (gym.Env) – The environment to be wrapped.
reset(**kwargs)[source]

gym.Env reset function.

step(action)[source]

gym.Env step function.

class Grayscale(env)[source]

Bases: gym.core.Wrapper

Grayscale wrapper for gym.Env, converting frames to grayscale.

Only works with gym.spaces.Box environment with 2D RGB frames. The last dimension (RGB) of environment observation space will be removed.

Example

env = gym.make(‘Env’) # env.observation_space = (100, 100, 3)

env_wrapped = Grayscale(gym.make(‘Env’)) # env.observation_space = (100, 100)

Parameters:env – gym.Env to wrap.
Raises:ValueError – If observation space shape is not 3 or environment is not gym.spaces.Box.
observation_space

gym.Env observation space.

reset()[source]

gym.Env reset function.

step(action)[source]

gym.Env step function.

class MaxAndSkip(env, skip=4)[source]

Bases: gym.core.Wrapper

Max and skip wrapper for gym.Env.

It returns only every skip-th frame. Action are repeated and rewards are sum for the skipped frames.

It also takes element-wise maximum over the last two consecutive frames, which helps algorithm deal with the problem of how certain Atari games only render their sprites every other game frame.

Parameters:
  • env – The environment to be wrapped.
  • skip – The environment only returns skip-th frame.
reset()[source]

gym.Env reset.

step(action)[source]

gym.Env step.

Repeat action, sum reward, and max over last two observations.

class Noop(env, noop_max=30)[source]

Bases: gym.core.Wrapper

Noop wrapper for gym.Env.

It samples initial states by taking random number of no-ops on reset. No-op is assumed to be action 0.

Parameters:
  • env (gym.Env) – The environment to be wrapped.
  • noop_max (int) – Maximum number no-op to be performed on reset.
reset(**kwargs)[source]

gym.Env reset function.

step(action)[source]

gym.Env step function.

class Resize(env, width, height)[source]

Bases: gym.core.Wrapper

gym.Env wrapper for resizing frame to (width, height).

Only works with gym.spaces.Box environment with 2D single channel frames.

Example

env = gym.make(‘Env’)
# env.observation_space = (100, 100)
env_wrapped = Resize(gym.make(‘Env’), width=64, height=64)
# env.observation_space = (64, 64)
Parameters:
  • env – gym.Env to wrap.
  • width – resized frame width.
  • height – resized frame height.
Raises:

ValueError – If observation space shape is not 2 or environment is not gym.spaces.Box.

observation_space

gym.Env observation space.

reset()[source]

gym.Env reset function.

step(action)[source]

gym.Env step function.

class StackFrames(env, n_frames)[source]

Bases: gym.core.Wrapper

gym.Env wrapper to stack multiple frames.

Useful for training feed-forward agents on dynamic games. Only works with gym.spaces.Box environment with 2D single channel frames.

Parameters:
  • env – gym.Env to wrap.
  • n_frames – number of frames to stack.
Raises:
  • ValueError – If observation space shape is not 2 or
  • environment is not gym.spaces.Box.
observation_space

gym.Env observation space.

reset()[source]

gym.Env reset function.

step(action)[source]

gym.Env step function.