-
Notifications
You must be signed in to change notification settings - Fork 60
/
atari_wrappers.py
313 lines (254 loc) · 10.1 KB
/
atari_wrappers.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
from collections import deque
import numpy as np
import gym
from gym import spaces
import cv2 # pytype:disable=import-error
cv2.ocl.setUseOpenCL(False)
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.
:param env: (Gym Environment) the environment to wrap
:param noop_max: (int) the maximum value of no-ops to run
"""
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):
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)
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, action):
return self.env.step(action)
class FireResetEnv(gym.Wrapper):
def __init__(self, env):
"""
Take action on reset for environments that are fixed until firing.
:param env: (Gym Environment) the environment to wrap
"""
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, action):
return self.env.step(action)
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.
:param env: (Gym Environment) the environment to wrap
"""
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 0 < lives < self.lives:
# for Qbert sometimes we stay in lives == 0 condtion for a few frames
# so its 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):
"""
Calls the Gym environment 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.
:param kwargs: Extra keywords passed to env.reset() call
:return: ([int] or [float]) the first observation of the environment
"""
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
class MaxAndSkipEnv(gym.Wrapper):
def __init__(self, env, skip=4):
"""
Return only every `skip`-th frame (frameskipping)
:param env: (Gym Environment) the environment
:param skip: (int) number of `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=env.observation_space.dtype)
self._skip = skip
def step(self, action):
"""
Step the environment with the given action
Repeat action, sum reward, and max over last observations.
:param action: ([int] or [float]) the action
:return: ([int] or [float], [float], [bool], dict) observation, reward, done, information
"""
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):
"""
clips the reward to {+1, 0, -1} by its sign.
:param env: (Gym Environment) the environment
"""
gym.RewardWrapper.__init__(self, env)
def reward(self, reward):
"""
Bin reward to {+1, 0, -1} by its sign.
:param reward: (float)
"""
return np.sign(reward)
class WarpFrame(gym.ObservationWrapper):
def __init__(self, env):
"""
Warp frames to 84x84 as done in the Nature paper and later work.
:param env: (Gym Environment) the environment
"""
gym.ObservationWrapper.__init__(self, env)
self.width = 84
self.height = 84
self.observation_space = spaces.Box(low=0, high=255, shape=(self.height, self.width, 1),
dtype=env.observation_space.dtype)
def observation(self, frame):
"""
returns the current observation from a frame
:param frame: ([int] or [float]) environment frame
:return: ([int] or [float]) the observation
"""
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
frame = cv2.resize(frame, (self.width, self.height), interpolation=cv2.INTER_AREA)
return frame[:, :, None]
class FrameStack(gym.Wrapper):
def __init__(self, env, n_frames):
"""Stack n_frames last frames.
Returns lazy array, which is much more memory efficient.
See Also
--------
stable_baselines.common.atari_wrappers.LazyFrames
:param env: (Gym Environment) the environment
:param n_frames: (int) the number of frames to stack
"""
gym.Wrapper.__init__(self, env)
self.n_frames = n_frames
self.frames = deque([], maxlen=n_frames)
shp = env.observation_space.shape
self.observation_space = spaces.Box(low=0, high=255, shape=(shp[0], shp[1], shp[2] * n_frames),
dtype=env.observation_space.dtype)
def reset(self, **kwargs):
obs = self.env.reset(**kwargs)
for _ in range(self.n_frames):
self.frames.append(obs)
return self._get_ob()
def step(self, action):
obs, reward, done, info = self.env.step(action)
self.frames.append(obs)
return self._get_ob(), reward, done, info
def _get_ob(self):
assert len(self.frames) == self.n_frames
return LazyFrames(list(self.frames))
class ScaledFloatFrame(gym.ObservationWrapper):
def __init__(self, env):
gym.ObservationWrapper.__init__(self, env)
self.observation_space = spaces.Box(low=0, high=1.0, 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
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 np.ndarray before being passed to the model.
:param frames: ([int] or [float]) environment frames
"""
self._frames = frames
self._out = None
def _force(self):
if self._out is None:
self._out = np.concatenate(self._frames, axis=2)
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 make_atari(env_id):
"""
Create a wrapped atari Environment
:param env_id: (str) the environment ID
:return: (Gym Environment) the wrapped atari environment
"""
env = gym.make(env_id)
assert 'NoFrameskip' in env.spec.id
env = NoopResetEnv(env, noop_max=30)
env = MaxAndSkipEnv(env, skip=4)
return env
def wrap_deepmind(env, episode_life=True, clip_rewards=True, frame_stack=False, scale=False):
"""
Configure environment for DeepMind-style Atari.
:param env: (Gym Environment) the atari environment
:param episode_life: (bool) wrap the episode life wrapper
:param clip_rewards: (bool) wrap the reward clipping wrapper
:param frame_stack: (bool) wrap the frame stacking wrapper
:param scale: (bool) wrap the scaling observation wrapper
:return: (Gym Environment) the wrapped atari environment
"""
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