强化学习 --baseline项目之gym中的Atari游戏的环境重写
gym中集成的atari游戏可用于DQN训练，但是操作还不够方便，于是baseline中专门对gym的环境重写，以更好地适应dqn的训练
从源码中可以看出，只需要重写两个函数 reset（）和step() ，由于render（）没有被重写，所以画面就没有被显示出来了
1.NoopResetEnv（）函数，功能：前30帧画面什么都不做，跳过。这有利于增加初始画面的随机性，不容易陷入过拟合
class NoopResetEnv(gym.Wrapper):
def __init__(self, env, noop_max=30):
"""Sample initial states by taking random number of no-ops on reset.
No-op is assumed to be action 0.
"""
gym.Wrapper.__init__(self, env)
self.noop_max = noop_max
self.override_num_noops = None
self.noop_action = 0
assert env.unwrapped.get_action_meanings()[0] == 'NOOP'
def reset(self, **kwargs):
""" Do no-op action for a number of steps in [1, noop_max]."""
self.env.reset(**kwargs)
if self.override_num_noops is not None:
noops = self.override_num_noops
else:
noops = self.unwrapped.np_random.randint(1, self.noop_max + 1) #pylint: disable=E1101
assert noops > 0
obs = None
for _ in range(noops):
obs, _, done, _ = self.env.step(self.noop_action)
if done:
obs = self.env.reset(**kwargs)
return obs
def step(self, ac):
return self.env.step(ac)
2.FireResetEnv() 功能：一直step（）到‘开火’为止
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)
3.EpisodicLifeEnv（） 功能：一般一个游戏玩家往往有多条命，但是为了更好的训练，该函数设置死掉一次就直接结束游戏，以便ai加强避免死亡的训练
class EpisodicLifeEnv(gym.Wrapper):
def __init__(self, env):
"""Make end-of-life == end-of-episode, but only reset on true game over.
Done by DeepMind for the DQN and co. since it helps value estimation.
"""
gym.Wrapper.__init__(self, env)
self.lives = 0
self.was_real_done = True
def step(self, action):
obs, reward, done, info = self.env.step(action)
self.was_real_done = done
# check current lives, make loss of life terminal,
# then update lives to handle bonus lives
lives = self.env.unwrapped.ale.lives()
if lives < self.lives and lives > 0:
# for Qbert sometimes we stay in lives == 0 condition for a few frames
# so it's important to keep lives > 0, so that we only reset once
# the environment advertises done.
done = True
self.lives = lives
return obs, reward, done, info
def reset(self, **kwargs):
"""Reset only when lives are exhausted.
This way all states are still reachable even though lives are episodic,
and the learner need not know about any of this behind-the-scenes.
"""
if self.was_real_done:
obs = self.env.reset(**kwargs)
else:
# no-op step to advance from terminal/lost life state
obs, _, _, _ = self.env.step(0)
self.lives = self.env.unwrapped.ale.lives()
return obs
4. MaxAndSkipEnv（）函数 。功能：跳过若干帧画面，并且取最后两针像素值的最大值。跳过若干帧的目的是加速训练，因为相邻帧之间的相似度太高，没必要全部拿来训练。取最后两帧的最大值的原因是Atari游戏中有些画面只在奇数帧中显示，有些只在偶数帧中显示。我们肉眼能看见游戏的全部画面是因为画面的频率很高而造成的假象。所以这样做是有必要的
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)
5.ClipRewardEnv（）函数 。功能：将游戏的奖励符号化。这里解释下原因：在论文《Human-level control through deep reinforcement learning》中，DeepMind 团队是用一个网络来同时玩49个Atari游戏，每个游戏玩5分钟。但是游戏不同游戏的奖励不一样，这样会造成网络学习到权重不统一，所以把所有游戏的奖励都符号化
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)
6.WarpFrame（）函数：图像处理函数，将原本的210x160x3的彩色图像编程84x84的灰度图像，在清晰度不受太大影响时，以增加程序的计算效率
class WarpFrame(gym.ObservationWrapper):
def __init__(self, env, width=84, height=84, grayscale=True, dict_space_key=None):
"""
Warp frames to 84x84 as done in the Nature paper and later work.
If the environment uses dictionary observations, `dict_space_key` can be specified which indicates which
observation should be warped.
"""
super().__init__(env)
self._width = width
self._height = height
self._grayscale = grayscale
self._key = dict_space_key
if self._grayscale:
num_colors = 1
else:
num_colors = 3
new_space = gym.spaces.Box(
low=0,
high=255,
shape=(self._height, self._width, num_colors),
dtype=np.uint8,
)
if self._key is None:
original_space = self.observation_space
self.observation_space = new_space
else:
original_space = self.observation_space.spaces[self._key]
self.observation_space.spaces[self._key] = new_space
assert original_space.dtype == np.uint8 and len(original_space.shape) == 3
def observation(self, obs):
if self._key is None:
frame = obs
else:
frame = obs[self._key]
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)
if self._key is None:
obs = frame
else:
obs = obs.copy()
obs[self._key] = frame
return obs
7.FrameStack（）函数：使用deque（），每次都将最后四帧当成状态，因为游戏中前后是具有相关性的，只使用一帧的话不能判断出游戏的状态，经过试验取4帧的效果比较好
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
# print('shp:',shp)
# print((shp[:-1] + (shp[-1] * k,)))
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))
8.ScaledFloatFrame（）函数：将像素量化成（0,1）的浮点数，方便神经网络训练
class ScaledFloatFrame(gym.ObservationWrapper):
def __init__(self, env):
gym.ObservationWrapper.__init__(self, env)
self.observation_space = gym.spaces.Box(low=0, high=1, shape=env.observation_space.shape, dtype=np.float32)
def observation(self, observation):
# careful! This undoes the memory optimization, use
# with smaller replay buffers only.
return np.array(observation).astype(np.float32) / 255.0
9.LazyFrames()函数：是去重函数，相同画面的图像就不重复存储了（然而我没看懂，为毛这样就能去重了？？？）
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]
def count(self):
frames = self._force()
return frames.shape[frames.ndim - 1]
def frame(self, i):
return self._force()[..., i]
10.make_atari（）函数：将前面的函数整合使用起来。以上想用哪个功能直接将这个函数传进去过一遍就行了
def make_atari(env_id, max_episode_steps=None):
env = gym.make(env_id)
assert 'NoFrameskip' in env.spec.id
env = NoopResetEnv(env, noop_max=30)
env = MaxAndSkipEnv(env, skip=4)
if max_episode_steps is not None:
env = TimeLimit(env, max_episode_steps=max_episode_steps) #step（）次数的限制
return env
11.TimeLimit（）函数：用于限制训练次数的函数，可以设置最大玩耍次数
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)
12.ClipActionsWrapper（）函数：用于把action限定在上下限的范围内的函数
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)
13.wrap_deepmind()函数：也是用于整合以上函数哪些用，哪些不用的
def wrap_deepmind(env, episode_life=True, clip_rewards=True, frame_stack=False, scale=False):
"""Configure environment for DeepMind-style Atari.
"""
if episode_life:
env = EpisodicLifeEnv(env)
if 'FIRE' in env.unwrapped.get_action_meanings():
env = FireResetEnv(env)
env = WarpFrame(env)
if scale:
env = ScaledFloatFrame(env)
if clip_rewards:
env = ClipRewardEnv(env)
if frame_stack:
env = FrameStack(env, 4)
return env
以上这就是baseline中atari_wrappers.py中的所有函数了，都是用于Atari游戏环境中方便强化学习使用的函数