Hugging Face's logo

Forkits
/
MLAgents-Pyramids

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-Pyramids
Model card Files Metrics Community
1
MLAgents-Pyramids
File size: 5,866 Bytes 
aa693a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8219146
aa693a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8219146
aa693a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8219146
aa693a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
default:
    trainer: ppo
    batch_size: 1024
    beta: 5.0e-3
    buffer_size: 10240
    epsilon: 0.2
    hidden_units: 128
    lambd: 0.95
    learning_rate: 3.0e-4
    learning_rate_schedule: linear
    max_steps: 5.0e5
    memory_size: 256
    normalize: false
    num_epoch: 3
    num_layers: 2
    time_horizon: 64
    sequence_length: 64
    summary_freq: 10000
    use_recurrent: false
    vis_encode_type: simple
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99

FoodCollector:
    normalize: false
    beta: 5.0e-3
    batch_size: 1024
    buffer_size: 10240
    max_steps: 2.0e6

Bouncer:
    normalize: true
    max_steps: 7.0e6
    num_layers: 2
    hidden_units: 64

PushBlock:
    max_steps: 1.5e7
    batch_size: 128
    buffer_size: 2048
    beta: 1.0e-2
    hidden_units: 256
    summary_freq: 60000
    time_horizon: 64
    num_layers: 2

SmallWallJump:
    max_steps: 5e6
    batch_size: 128
    buffer_size: 2048
    beta: 5.0e-3
    hidden_units: 256
    summary_freq: 20000
    time_horizon: 128
    num_layers: 2
    normalize: false

BigWallJump:
    max_steps: 2e7
    batch_size: 128
    buffer_size: 2048
    beta: 5.0e-3
    hidden_units: 256
    summary_freq: 20000
    time_horizon: 128
    num_layers: 2
    normalize: false

Pyramids:
    summary_freq: 30000
    time_horizon: 128
    batch_size: 128
    buffer_size: 2048
    hidden_units: 512
    num_layers: 2
    beta: 1.0e-2
    max_steps: 1.0e7
    num_epoch: 3
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99
        curiosity:
            strength: 0.02
            gamma: 0.99
            encoding_size: 256

VisualPyramids:
    time_horizon: 128
    batch_size: 64
    buffer_size: 2024
    hidden_units: 256
    num_layers: 1
    beta: 1.0e-2
    max_steps: 1.0e7
    num_epoch: 3
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99
        curiosity:
            strength: 0.01
            gamma: 0.99
            encoding_size: 256

3DBall:
    normalize: true
    batch_size: 64
    buffer_size: 12000
    summary_freq: 12000
    time_horizon: 1000
    lambd: 0.99
    beta: 0.001

3DBallHard:
    normalize: true
    batch_size: 1200
    buffer_size: 12000
    summary_freq: 12000
    time_horizon: 1000
    max_steps: 5.0e5
    beta: 0.001
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.995

Tennis:
    normalize: true
    max_steps: 5.0e7
    learning_rate_schedule: constant
    batch_size: 1024
    buffer_size: 10240
    hidden_units: 256
    time_horizon: 1000
    self_play:
        window: 10
        play_against_current_self_ratio: 0.5
        save_steps: 50000
        swap_steps: 50000

Soccer:
    normalize: false
    max_steps: 5.0e7
    learning_rate_schedule: constant
    batch_size: 2048
    buffer_size: 20480
    hidden_units: 512
    time_horizon: 1000
    num_layers: 2
    self_play:
        window: 10
        play_against_current_self_ratio: 0.5
        save_steps: 50000
        swap_steps: 50000

CrawlerStatic:
    normalize: true
    num_epoch: 3
    time_horizon: 1000
    batch_size: 2024
    buffer_size: 20240
    max_steps: 1e7
    summary_freq: 30000
    num_layers: 3
    hidden_units: 512
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.995

CrawlerDynamic:
    normalize: true
    num_epoch: 3
    time_horizon: 1000
    batch_size: 2024
    buffer_size: 20240
    max_steps: 1e7
    summary_freq: 30000
    num_layers: 3
    hidden_units: 512
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.995

Walker:
    normalize: true
    num_epoch: 3
    time_horizon: 1000
    batch_size: 2048
    buffer_size: 20480
    max_steps: 2e7
    summary_freq: 30000
    num_layers: 3
    hidden_units: 512
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.995

Reacher:
    normalize: true
    num_epoch: 3
    time_horizon: 1000
    batch_size: 2024
    buffer_size: 20240
    max_steps: 2e7
    summary_freq: 60000
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.995

Hallway:
    use_recurrent: true
    sequence_length: 64
    num_layers: 2
    hidden_units: 128
    memory_size: 256
    beta: 1.0e-2
    num_epoch: 3
    buffer_size: 1024
    batch_size: 128
    max_steps: 1.0e7
    summary_freq: 10000
    time_horizon: 64

VisualHallway:
    use_recurrent: true
    sequence_length: 64
    num_layers: 1
    hidden_units: 128
    memory_size: 256
    beta: 1.0e-2
    num_epoch: 3
    buffer_size: 1024
    batch_size: 64
    max_steps: 1.0e7
    summary_freq: 10000
    time_horizon: 64

VisualPushBlock:
    use_recurrent: true
    sequence_length: 32
    num_layers: 1
    hidden_units: 128
    memory_size: 256
    beta: 1.0e-2
    num_epoch: 3
    buffer_size: 1024
    batch_size: 64
    max_steps: 3.0e6
    summary_freq: 60000
    time_horizon: 64

GridWorld:
    batch_size: 32
    normalize: false
    num_layers: 1
    hidden_units: 256
    beta: 5.0e-3
    buffer_size: 256
    max_steps: 500000
    summary_freq: 20000
    time_horizon: 5
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.9

Basic:
    batch_size: 32
    normalize: false
    num_layers: 1
    hidden_units: 20
    beta: 5.0e-3
    buffer_size: 256
    max_steps: 5.0e5
    summary_freq: 2000
    time_horizon: 3
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.9

AircraftLearning:
    summary_freq: 32000
    time_horizon: 128
    batch_size: 2048 #512
    buffer_size: 20480 #4096
    hidden_units: 256 #128
    num_layers: 2
    beta: 1.0e-2
    max_steps: 5.0e7
    num_epoch: 3
    reward_signals:
        extrinsic:
            strength: 1.0
            gamma: 0.99