-
Notifications
You must be signed in to change notification settings - Fork 533
/
Copy pathppo.yml
385 lines (363 loc) · 8.16 KB
/
ppo.yml
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
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
atari:
env_wrapper:
- stable_baselines3.common.atari_wrappers.AtariWrapper
frame_stack: 4
policy: 'CnnPolicy'
n_envs: 8
n_steps: 128
n_epochs: 4
batch_size: 256
n_timesteps: !!float 1e7
learning_rate: lin_2.5e-4
clip_range: lin_0.1
vf_coef: 0.5
ent_coef: 0.01
Pendulum-v0:
n_envs: 8
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: !!float 3e-4
clip_range: 0.2
# Tuned
CartPole-v1:
n_envs: 8
n_timesteps: !!float 1e5
policy: 'MlpPolicy'
n_steps: 32
batch_size: 256
gae_lambda: 0.8
gamma: 0.98
n_epochs: 20
ent_coef: 0.0
learning_rate: lin_0.001
clip_range: lin_0.2
MountainCar-v0:
normalize: true
n_envs: 16
n_timesteps: !!float 1e6
policy: 'MlpPolicy'
n_steps: 16
gae_lambda: 0.98
gamma: 0.99
n_epochs: 4
ent_coef: 0.0
# Tuned
MountainCarContinuous-v0:
normalize: true
n_envs: 1
n_timesteps: !!float 20000
policy: 'MlpPolicy'
batch_size: 256
n_steps: 8
gamma: 0.9999
learning_rate: !!float 7.77e-05
ent_coef: 0.00429
clip_range: 0.1
n_epochs: 10
gae_lambda: 0.9
max_grad_norm: 5
vf_coef: 0.19
use_sde: True
policy_kwargs: "dict(log_std_init=-3.29, ortho_init=False)"
Acrobot-v1:
normalize: true
n_envs: 16
n_timesteps: !!float 1e6
policy: 'MlpPolicy'
n_steps: 256
gae_lambda: 0.94
gamma: 0.99
n_epochs: 4
ent_coef: 0.0
BipedalWalker-v3:
normalize: true
n_envs: 16
n_timesteps: !!float 5e6
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.001
learning_rate: !!float 2.5e-4
clip_range: 0.2
BipedalWalkerHardcore-v3:
normalize: true
n_envs: 16
n_timesteps: !!float 10e7
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.001
learning_rate: lin_2.5e-4
clip_range: lin_0.2
LunarLander-v2:
n_envs: 16
n_timesteps: !!float 1e6
policy: 'MlpPolicy'
n_steps: 1024
batch_size: 64
gae_lambda: 0.98
gamma: 0.999
n_epochs: 4
ent_coef: 0.01
LunarLanderContinuous-v2:
n_envs: 16
n_timesteps: !!float 1e6
policy: 'MlpPolicy'
n_steps: 1024
batch_size: 64
gae_lambda: 0.98
gamma: 0.999
n_epochs: 4
ent_coef: 0.01
# Tuned
HalfCheetahBulletEnv-v0:
env_wrapper: sb3_contrib.common.wrappers.TimeFeatureWrapper
normalize: true
n_envs: 16
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
batch_size: 128
n_steps: 512
gamma: 0.99
gae_lambda: 0.9
n_epochs: 20
ent_coef: 0.0
sde_sample_freq: 4
max_grad_norm: 0.5
vf_coef: 0.5
learning_rate: !!float 3e-5
use_sde: True
clip_range: 0.4
policy_kwargs: "dict(log_std_init=-2,
ortho_init=False,
activation_fn=nn.ReLU,
net_arch=[dict(pi=[256, 256], vf=[256, 256])]
)"
# Tuned
AntBulletEnv-v0:
env_wrapper: sb3_contrib.common.wrappers.TimeFeatureWrapper
normalize: true
n_envs: 16
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
batch_size: 128
n_steps: 512
gamma: 0.99
gae_lambda: 0.9
n_epochs: 20
ent_coef: 0.0
sde_sample_freq: 4
max_grad_norm: 0.5
vf_coef: 0.5
learning_rate: !!float 3e-5
use_sde: True
clip_range: 0.4
policy_kwargs: "dict(log_std_init=-1,
ortho_init=False,
activation_fn=nn.ReLU,
net_arch=[dict(pi=[256, 256], vf=[256, 256])]
)"
# Tuned
Walker2DBulletEnv-v0:
env_wrapper: sb3_contrib.common.wrappers.TimeFeatureWrapper
normalize: true
n_envs: 16
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
batch_size: 128
n_steps: 512
gamma: 0.99
gae_lambda: 0.92
n_epochs: 20
ent_coef: 0.0
sde_sample_freq: 4
max_grad_norm: 0.5
vf_coef: 0.5
learning_rate: !!float 3e-5
use_sde: True
clip_range: lin_0.4
policy_kwargs: "dict(log_std_init=-2,
ortho_init=False,
activation_fn=nn.ReLU,
net_arch=[dict(pi=[256, 256], vf=[256, 256])]
)"
# Tuned
HopperBulletEnv-v0:
env_wrapper: sb3_contrib.common.wrappers.TimeFeatureWrapper
normalize: true
n_envs: 16
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
batch_size: 128
n_steps: 512
gamma: 0.99
gae_lambda: 0.92
n_epochs: 20
ent_coef: 0.0
sde_sample_freq: 4
max_grad_norm: 0.5
vf_coef: 0.5
learning_rate: !!float 3e-5
use_sde: True
clip_range: lin_0.4
policy_kwargs: "dict(log_std_init=-2,
ortho_init=False,
activation_fn=nn.ReLU,
net_arch=[dict(pi=[256, 256], vf=[256, 256])]
)"
# Tuned
ReacherBulletEnv-v0:
env_wrapper: sb3_contrib.common.wrappers.TimeFeatureWrapper
normalize: true
n_envs: 8
n_timesteps: !!float 1e6
policy: 'MlpPolicy'
batch_size: 64
n_steps: 512
gamma: 0.99
gae_lambda: 0.9
n_epochs: 20
ent_coef: 0.0
sde_sample_freq: 4
max_grad_norm: 0.5
vf_coef: 0.5
learning_rate: !!float 3e-5
use_sde: True
clip_range: lin_0.4
policy_kwargs: "dict(log_std_init=-2.7,
ortho_init=False,
activation_fn=nn.ReLU,
net_arch=[dict(pi=[256, 256], vf=[256, 256])]
)"
MinitaurBulletEnv-v0:
normalize: true
n_envs: 8
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: 2.5e-4
clip_range: 0.2
MinitaurBulletDuckEnv-v0:
normalize: true
n_envs: 8
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: 2.5e-4
clip_range: 0.2
# To be tuned
HumanoidBulletEnv-v0:
normalize: true
n_envs: 8
n_timesteps: !!float 1e7
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: 2.5e-4
clip_range: 0.2
InvertedDoublePendulumBulletEnv-v0:
normalize: true
n_envs: 8
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: 2.5e-4
clip_range: 0.2
InvertedPendulumSwingupBulletEnv-v0:
normalize: true
n_envs: 8
n_timesteps: !!float 2e6
policy: 'MlpPolicy'
n_steps: 2048
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: 2.5e-4
clip_range: 0.2
# Following https://github.com/lcswillems/rl-starter-files
MiniGrid-DoorKey-5x5-v0:
env_wrapper: gym_minigrid.wrappers.FlatObsWrapper # requires --gym-packages gym_minigrid
normalize: true
n_envs: 8 # number of environment copies running in parallel
n_timesteps: !!float 1e5
policy: MlpPolicy
n_steps: 128 # batch size is n_steps * n_env
batch_size: 64 # Number of training minibatches per update
gae_lambda: 0.95 # Factor for trade-off of bias vs variance for Generalized Advantage Estimator
gamma: 0.99
n_epochs: 10 # Number of epoch when optimizing the surrogate
ent_coef: 0.0 # Entropy coefficient for the loss caculation
learning_rate: 2.5e-4 # The learning rate, it can be a function
clip_range: 0.2 # Clipping parameter, it can be a function
MiniGrid-FourRooms-v0:
env_wrapper: gym_minigrid.wrappers.FlatObsWrapper # requires --gym-packages gym_minigrid
normalize: true
n_envs: 8
n_timesteps: !!float 4e6
policy: 'MlpPolicy'
n_steps: 512
batch_size: 64
gae_lambda: 0.95
gamma: 0.99
n_epochs: 10
ent_coef: 0.0
learning_rate: 2.5e-4
clip_range: 0.2
CarRacing-v0:
env_wrapper:
- gym.wrappers.resize_observation.ResizeObservation:
shape: 64
- gym.wrappers.gray_scale_observation.GrayScaleObservation:
keep_dim: true
frame_stack: 4
n_envs: 8
n_timesteps: !!float 1e6
policy: 'CnnPolicy'
batch_size: 128
n_steps: 512
gamma: 0.99
gae_lambda: 0.9
n_epochs: 20
ent_coef: 0.0
sde_sample_freq: 4
max_grad_norm: 0.5
vf_coef: 0.5
learning_rate: !!float 3e-5
use_sde: True
clip_range: 0.4
policy_kwargs: "dict(log_std_init=-2,
ortho_init=False,
)"