wrappers.py

#From https://github.com/openai/baselines/blob/master/baselines/common/atari_wrappers.py
import numpy as np
import os
os.environ.setdefault('PATH', '')
from collections import deque
import gym
from gym import spaces
import cv2
cv2.ocl.setUseOpenCL(False)


class FireResetEnv(gym.Wrapper):
    def __init__(self, env):
        """Take action on reset for environments that are fixed until firing."""
        gym.Wrapper.__init__(self, env)
        assert env.unwrapped.get_action_meanings()[1] == 'FIRE'
        assert len(env.unwrapped.get_action_meanings()) >= 3

    def reset(self, **kwargs):
        self.env.reset(**kwargs)
        obs, _, done, _ = self.env.step(1)
        if done:
            self.env.reset(**kwargs)
        obs, _, done, _ = self.env.step(2)
        if done:
            self.env.reset(**kwargs)
        return obs

    def step(self, ac):
        return self.env.step(ac)


class MaxAndSkipEnv(gym.Wrapper):
    def __init__(self, env, skip=4):
        """Return only every `skip`-th frame"""
        gym.Wrapper.__init__(self, env)
        # most recent raw observations (for max pooling across time steps)
        self._obs_buffer = np.zeros((2,)+env.observation_space.shape, dtype=np.uint8)
        self._skip = skip

    def step(self, action):
        """Repeat action, sum reward, and max over last observations."""
        total_reward = 0.0
        done = None
        for i in range(self._skip):
            obs, reward, done, info = self.env.step(action)
            if i == self._skip - 2: self._obs_buffer[0] = obs
            if i == self._skip - 1: self._obs_buffer[1] = obs
            total_reward += reward
            if done:
                break
        # Note that the observation on the done=True frame
        # doesn't matter
        max_frame = self._obs_buffer.max(axis=0)

        return max_frame, total_reward, done, info

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


class ClipRewardEnv(gym.RewardWrapper):
    def __init__(self, env):
        gym.RewardWrapper.__init__(self, env)

    def reward(self, reward):
        """Bin reward to {+1, 0, -1} by its sign."""
        return np.sign(reward)


class WarpFrame(gym.ObservationWrapper):
    def __init__(self, env, width=84, height=84, grayscale=True):
        """Warp frames to 84x84 as done in the Nature paper and later work."""
        gym.ObservationWrapper.__init__(self, env)
        self.width = width
        self.height = height
        self.grayscale = grayscale
        if self.grayscale:
            self.observation_space = spaces.Box(low=0, high=255,
                shape=(self.height, self.width, 1), dtype=np.uint8)
        else:
            self.observation_space = spaces.Box(low=0, high=255,
                shape=(self.height, self.width, 3), dtype=np.uint8)

    def observation(self, frame):
        if self.grayscale:
            frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
        frame = cv2.resize(frame, (self.width, self.height), interpolation=cv2.INTER_AREA)
        if self.grayscale:
            frame = np.expand_dims(frame, -1)
        return frame


class LazyFrames(object):
    def __init__(self, frames):
        """This object ensures that common frames between the observations are only stored once.
        It exists purely to optimize memory usage which can be huge for DQN's 1M frames replay
        buffers.
        This object should only be converted to numpy array before being passed to the model.
        You'd not believe how complex the previous solution was."""
        self._frames = frames
        self._out = None

    def _force(self):
        if self._out is None:
            self._out = np.concatenate(self._frames, axis=-1)
            self._frames = None
        return self._out

    def __array__(self, dtype=None):
        out = self._force()
        if dtype is not None:
            out = out.astype(dtype)
        return out

    def __len__(self):
        return len(self._force())

    def __getitem__(self, i):
        return self._force()[i]


class FrameStack(gym.Wrapper):
    def __init__(self, env, k):
        """Stack k last frames.
        Returns lazy array, which is much more memory efficient.
        See Also
        --------
        baselines.common.atari_wrappers.LazyFrames
        """
        gym.Wrapper.__init__(self, env)
        self.k = k
        self.frames = deque([], maxlen=k)
        shp = env.observation_space.shape
        self.observation_space = spaces.Box(low=0, high=255, shape=(shp[:-1] + (shp[-1] * k,)), dtype=env.observation_space.dtype)

    def reset(self):
        ob = self.env.reset()
        for _ in range(self.k):
            self.frames.append(ob)
        return self._get_ob()

    def step(self, action):
        ob, reward, done, info = self.env.step(action)
        self.frames.append(ob)
        return self._get_ob(), reward, done, info

    def _get_ob(self):
        assert len(self.frames) == self.k
        return LazyFrames(list(self.frames))


def wrapper(env):
    env = MaxAndSkipEnv(env, skip=4)
    if 'FIRE' in env.unwrapped.get_action_meanings():
       env = FireResetEnv(env)
    env = WarpFrame(env)
    env = FrameStack(env, 4)
    #With this you can clip reward to 0, 1 and -1
    #env = ClipRewardEnv(env)
    return env