File size: 7,629 Bytes
05dcd82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
CartPole-v1: &cartpole-defaults
  n_timesteps: !!float 1e5
  env_hyperparams:
    n_envs: 8
  algo_hyperparams:
    n_steps: 32
    batch_size: 256
    n_epochs: 20
    gae_lambda: 0.8
    gamma: 0.98
    ent_coef: 0.0
    learning_rate: 0.001
    learning_rate_decay: linear
    clip_range: 0.2
    clip_range_decay: linear
  eval_params:
    step_freq: !!float 2.5e4

CartPole-v0:
  <<: *cartpole-defaults
  n_timesteps: !!float 5e4

MountainCar-v0:
  n_timesteps: !!float 1e6
  env_hyperparams:
    normalize: true
    n_envs: 16
  algo_hyperparams:
    n_steps: 16
    n_epochs: 4
    gae_lambda: 0.98
    gamma: 0.99
    ent_coef: 0.0

MountainCarContinuous-v0:
  n_timesteps: !!float 1e5
  env_hyperparams:
    normalize: true
    n_envs: 4
  # policy_hyperparams:
  #   init_layers_orthogonal: false
  #   log_std_init: -3.29
  #   use_sde: true
  algo_hyperparams:
    n_steps: 512
    batch_size: 256
    n_epochs: 10
    learning_rate: !!float 7.77e-5
    ent_coef: 0.01 # 0.00429
    ent_coef_decay: linear
    clip_range: 0.1
    gae_lambda: 0.9
    max_grad_norm: 5
    vf_coef: 0.19
  eval_params:
    step_freq: 5000

Acrobot-v1:
  n_timesteps: !!float 1e6
  env_hyperparams:
    n_envs: 16
    normalize: true
  algo_hyperparams:
    n_steps: 256
    n_epochs: 4
    gae_lambda: 0.94
    gamma: 0.99
    ent_coef: 0.0

LunarLander-v2:
  n_timesteps: !!float 1e6
  env_hyperparams:
    n_envs: 16
  algo_hyperparams:
    n_steps: 1024
    batch_size: 64
    n_epochs: 4
    gae_lambda: 0.98
    gamma: 0.999
    ent_coef: 0.01
    ent_coef_decay: linear
    normalize_advantage: false

CarRacing-v0: &carracing-defaults
  n_timesteps: !!float 4e6
  env_hyperparams:
    n_envs: 8
    frame_stack: 4
  policy_hyperparams: &carracing-policy-defaults
    use_sde: true
    log_std_init: -2
    init_layers_orthogonal: false
    activation_fn: relu
    share_features_extractor: false
    cnn_feature_dim: 256
    hidden_sizes: [256]
  algo_hyperparams:
    n_steps: 512
    batch_size: 128
    n_epochs: 10
    learning_rate: !!float 1e-4
    learning_rate_decay: linear
    gamma: 0.99
    gae_lambda: 0.95
    ent_coef: 0.0
    sde_sample_freq: 4
    max_grad_norm: 0.5
    vf_coef: 0.5
    clip_range: 0.2

impala-CarRacing-v0:
  <<: *carracing-defaults
  env_id: CarRacing-v0
  policy_hyperparams:
    <<: *carracing-policy-defaults
    cnn_style: impala
    init_layers_orthogonal: true
    cnn_layers_init_orthogonal: false
    hidden_sizes: []

# BreakoutNoFrameskip-v4
# PongNoFrameskip-v4
# SpaceInvadersNoFrameskip-v4
# QbertNoFrameskip-v4
_atari: &atari-defaults
  n_timesteps: !!float 1e7
  env_hyperparams: &atari-env-defaults
    n_envs: 8
    frame_stack: 4
    no_reward_timeout_steps: 1000
    no_reward_fire_steps: 500
    vec_env_class: subproc
  policy_hyperparams: &atari-policy-defaults
    activation_fn: relu
  algo_hyperparams:
    n_steps: 128
    batch_size: 256
    n_epochs: 4
    learning_rate: !!float 2.5e-4
    learning_rate_decay: linear
    clip_range: 0.1
    clip_range_decay: linear
    vf_coef: 0.5
    ent_coef: 0.01
  eval_params:
    deterministic: false

debug-PongNoFrameskip-v4:
  <<: *atari-defaults
  device: cpu
  env_id: PongNoFrameskip-v4
  env_hyperparams:
    <<: *atari-env-defaults
    vec_env_class: dummy

_impala-atari: &impala-atari-defaults
  <<: *atari-defaults
  policy_hyperparams:
    <<: *atari-policy-defaults
    cnn_style: impala
    cnn_feature_dim: 256
    init_layers_orthogonal: true
    cnn_layers_init_orthogonal: false

impala-PongNoFrameskip-v4:
  <<: *impala-atari-defaults
  env_id: PongNoFrameskip-v4

impala-BreakoutNoFrameskip-v4:
  <<: *impala-atari-defaults
  env_id: BreakoutNoFrameskip-v4

impala-SpaceInvadersNoFrameskip-v4:
  <<: *impala-atari-defaults
  env_id: SpaceInvadersNoFrameskip-v4

impala-QbertNoFrameskip-v4:
  <<: *impala-atari-defaults
  env_id: QbertNoFrameskip-v4

HalfCheetahBulletEnv-v0: &pybullet-defaults
  n_timesteps: !!float 2e6
  env_hyperparams: &pybullet-env-defaults
    n_envs: 16
    normalize: true
  policy_hyperparams: &pybullet-policy-defaults
    pi_hidden_sizes: [256, 256]
    v_hidden_sizes: [256, 256]
    activation_fn: relu
  algo_hyperparams: &pybullet-algo-defaults
    n_steps: 512
    batch_size: 128
    n_epochs: 20
    gamma: 0.99
    gae_lambda: 0.9
    ent_coef: 0.0
    max_grad_norm: 0.5
    vf_coef: 0.5
    learning_rate: !!float 3e-5
    clip_range: 0.4

AntBulletEnv-v0:
  <<: *pybullet-defaults
  policy_hyperparams:
    <<: *pybullet-policy-defaults
  algo_hyperparams:
    <<: *pybullet-algo-defaults

Walker2DBulletEnv-v0:
  <<: *pybullet-defaults
  algo_hyperparams:
    <<: *pybullet-algo-defaults
    clip_range_decay: linear

HopperBulletEnv-v0:
  <<: *pybullet-defaults
  algo_hyperparams:
    <<: *pybullet-algo-defaults
    clip_range_decay: linear

HumanoidBulletEnv-v0:
  <<: *pybullet-defaults
  n_timesteps: !!float 1e7
  env_hyperparams:
    <<: *pybullet-env-defaults
    n_envs: 8
  policy_hyperparams:
    <<: *pybullet-policy-defaults
    # log_std_init: -1
  algo_hyperparams:
    <<: *pybullet-algo-defaults
    n_steps: 2048
    batch_size: 64
    n_epochs: 10
    gae_lambda: 0.95
    learning_rate: !!float 2.5e-4
    clip_range: 0.2

_procgen: &procgen-defaults
  env_hyperparams: &procgen-env-defaults
    is_procgen: true
    n_envs: 64
    # grayscale: false
    # frame_stack: 4
    normalize: true # procgen only normalizes reward
  policy_hyperparams: &procgen-policy-defaults
    activation_fn: relu
    cnn_style: impala
    cnn_feature_dim: 256
    init_layers_orthogonal: true
    cnn_layers_init_orthogonal: false
  algo_hyperparams: &procgen-algo-defaults
    gamma: 0.999
    gae_lambda: 0.95
    n_steps: 256
    batch_size: 2048
    n_epochs: 3
    ent_coef: 0.01
    clip_range: 0.2
    # clip_range_decay: linear
    clip_range_vf: 0.2
    learning_rate: !!float 5e-4
    # learning_rate_decay: linear
    vf_coef: 0.5
  eval_params: &procgen-eval-defaults
    ignore_first_episode: true
    # deterministic: false
    step_freq: !!float 1e5

_procgen-easy: &procgen-easy-defaults
  <<: *procgen-defaults
  n_timesteps: !!float 25e6
  env_hyperparams: &procgen-easy-env-defaults
    <<: *procgen-env-defaults
    make_kwargs:
      distribution_mode: easy

procgen-coinrun-easy: &coinrun-easy-defaults
  <<: *procgen-easy-defaults
  env_id: coinrun

debug-procgen-coinrun:
  <<: *coinrun-easy-defaults
  device: cpu

procgen-starpilot-easy:
  <<: *procgen-easy-defaults
  env_id: starpilot

procgen-bossfight-easy:
  <<: *procgen-easy-defaults
  env_id: bossfight

procgen-bigfish-easy:
  <<: *procgen-easy-defaults
  env_id: bigfish

_procgen-hard: &procgen-hard-defaults
  <<: *procgen-defaults
  n_timesteps: !!float 200e6
  env_hyperparams: &procgen-hard-env-defaults
    <<: *procgen-env-defaults
    n_envs: 256
    make_kwargs:
      distribution_mode: hard
  algo_hyperparams:
    <<: *procgen-algo-defaults
    batch_size: 8192
  eval_params:
    <<: *procgen-eval-defaults
    step_freq: !!float 5e5

procgen-starpilot-hard: &procgen-starpilot-hard-defaults
  <<: *procgen-hard-defaults
  env_id: starpilot

procgen-starpilot-hard-2xIMPALA:
  <<: *procgen-starpilot-hard-defaults
  policy_hyperparams:
    <<: *procgen-policy-defaults
    impala_channels: [32, 64, 64]

procgen-starpilot-hard-2xIMPALA-fat:
  <<: *procgen-starpilot-hard-defaults
  policy_hyperparams:
    <<: *procgen-policy-defaults
    impala_channels: [32, 64, 64]
    cnn_feature_dim: 512

procgen-starpilot-hard-4xIMPALA:
  <<: *procgen-starpilot-hard-defaults
  policy_hyperparams:
    <<: *procgen-policy-defaults
    impala_channels: [64, 128, 128]