CatkinChen commited on
Commit
d744a97
·
verified ·
1 Parent(s): e9f9d31

Add training data

Browse files
Files changed (1) hide show
  1. training_data.json +219 -219
training_data.json CHANGED
@@ -1,227 +1,227 @@
1
  {
2
  "train_losses": [
3
- -0.0008496094378642738,
4
- 0.0009179687476716936,
5
- -0.0009375000954605639,
6
- -0.0007324219914153218,
7
- 0.00029296864522621036,
8
- 0.0004882811335846782,
9
- -0.002900390885770321,
10
- -0.002500000176951289,
11
- -0.002753906650468707,
12
- 0.0013671874767169356,
13
- -0.006035156548023224,
14
- 0.0018066405318677425,
15
- -0.003808594075962901,
16
- -0.0008789064595475793,
17
- -0.001435547019354999,
18
- 0.0007617187220603228,
19
- -0.0004296876722946763,
20
- -0.0008496094960719347,
21
- 0.0003906248603016138,
22
- -0.0016210938338190317,
23
- 0.0007617187220603228,
24
- -1.1641532182693481e-10,
25
- 0.00014648435171693563,
26
- -0.0014160159043967724,
27
- 0.0005078124231658876,
28
- -0.001171874930150807,
29
- 0.0004687499604187906,
30
- -0.0009667969425208867,
31
- 0.0006347656599245965,
32
- 5.859369412064552e-05,
33
- 0.0004199217655695975,
34
- -0.00025390629889443517,
35
- 0.0012207030085846782,
36
- -0.0019042971543967724,
37
- -0.0004296876140870154,
38
- -0.0038476563058793545,
39
- -0.0026855471078306437,
40
- -0.0006933595286682248,
41
- 0.00032226555049419403,
42
- -0.001757812569849193,
43
- 0.00045898425742052495,
44
- 0.0006640624487772584,
45
- -0.0008398438803851604,
46
- 0.0015234374441206455,
47
- 0.0003027342027053237,
48
- -0.0018847656901925802,
49
- 0.00032226555049419403,
50
- 0.0008593749371357262,
51
- -0.0014843749813735485,
52
- -0.0016113283345475793,
53
- 0.00012695303303189576,
54
- -0.00012695323675870895,
55
  -0.002119140699505806,
56
- -0.0027929688803851604,
57
- -1.9531347788870335e-05,
58
- 0.00017578114056959748,
59
- -0.0007324219332076609,
60
- 0.0007910155691206455,
61
- -0.0006347658345475793,
62
- 0.00029296870343387127,
63
- -0.0011718750465661287,
64
- -0.0012890626676380634,
65
- -0.0016699221450835466,
66
- 0.001054687425494194,
67
- -0.0024414064828306437,
68
- 0.0011425780830904841,
69
- -0.0007128907600417733,
70
- 0.0008984374580904841,
71
- -0.0008496093796566129,
72
- -0.001875000074505806,
73
- 0.0001757811987772584,
74
- -0.004121094010770321,
75
- -0.0012011718936264515,
76
- -0.001142578199505806,
77
- 0.0006054687546566129,
78
- -0.0010156250791624188,
79
- -0.0016503909137099981,
80
- -0.0008593752281740308,
81
- -0.001386718824505806,
82
- -0.006171875633299351,
83
- 0.0006835936801508069,
84
- -0.0015625001396983862,
85
- -7.812515832483768e-05,
86
- 2.9296788852661848e-05,
87
- -0.0012500002048909664,
88
- 0.0012695312034338713,
89
- -0.0020214845426380634,
90
- 0.00016601555398665369,
91
- -0.0002441406832076609,
92
- -0.0028320313431322575,
93
- -0.0036523439921438694,
94
- -0.00028320320416241884,
95
- -0.0007031250861473382,
96
- -0.002626953413709998,
97
- -0.0016601562965661287,
98
- -0.0006738282972946763,
99
- -0.0016015626024454832,
100
- -0.000859375111758709,
101
- -0.0013281252468004823,
102
- 0.0005468748277053237,
103
- 0.0009179686312563717,
104
- -0.0018554688431322575,
105
- -0.0017773439176380634,
106
- 0.0010839843889698386,
107
- -0.0005078125977888703,
108
- -0.0017382812220603228,
109
- -0.0006835937965661287,
110
- -0.0006347658345475793,
111
- 0.0007519531063735485,
112
- 0.000429687526775524,
113
- 0.0018164061475545168,
114
  -0.0008886720170266926,
115
- -0.0014062500558793545,
116
- -0.0027246095705777407,
117
- -0.0007031250279396772,
118
- -0.004033203236758709,
119
- -0.0029296877328306437,
120
- -0.0007324219914153218,
121
- -0.0010058594634756446,
122
- -0.0029980468098074198,
123
- 0.000400390534196049,
124
- -0.0008105469751171768,
125
- -0.0025585938710719347,
126
- -0.003867187537252903,
127
- -0.0025585938710719347,
128
- 9.765499271452427e-06,
129
- -0.0030957034323364496,
130
- -0.003076172200962901,
131
- -0.00390625,
132
- -0.0018554688431322575,
133
- -0.0032421876676380634,
134
- -0.0009765626164153218,
135
- -0.00459960987791419,
136
- -6.83594262227416e-05,
137
- -0.0009179688640870154,
138
- -0.0009570313850417733,
139
- -0.0007812500698491931,
140
- -0.0010351563105359674,
141
- -0.0019726562313735485,
142
- -1.9531231373548508e-05,
143
- -0.002978515811264515,
144
- -0.0004785157507285476,
145
- -0.0005371094448491931,
146
- -0.0022265624720603228,
147
- -0.0009667969425208867,
148
- -0.0006347657181322575,
149
- -0.000664062681607902,
150
- 0.0008886718424037099,
151
- 8.789054118096828e-05,
152
- 0.0013281248975545168,
153
  -0.00018554690177552402,
154
- 0.0011230468517169356,
155
- -0.0016503907972946763,
156
- -0.002900390885770321,
157
- -0.0006542970659211278,
158
- -0.0023925784043967724,
159
- -0.0018652344588190317,
160
- 0.00019531240104697645,
161
- 0.0015136718284338713,
162
- -0.0008105470333248377,
163
- -0.0009082031319849193,
164
- -0.00019531254656612873,
165
- -0.0001367188524454832,
166
- -0.0019824220798909664,
167
- -0.0007617188384756446,
168
- 0.0013574217446148396,
169
- -0.0008496093796566129,
170
- -0.0030078126583248377,
171
- 0.0011328124674037099,
172
- -0.0018261719960719347,
173
- -0.0002441406832076609,
174
- -0.0022363283205777407,
175
- 0.0003515623975545168,
176
- 0.0002539060660637915,
177
- -0.0026855471078306437,
178
- -0.0016699220286682248,
179
- -0.0008398438803851604,
180
- 0.001376952975988388,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
181
  1.9531144062057137e-05,
182
- 0.0009765624417923391,
183
- -0.0017480469541624188,
184
- 0.0002832030295394361,
185
- -0.0009472656529396772,
186
- -0.0008984376327134669,
187
- -0.004609375260770321,
188
- -0.0008496096124872565,
189
- 0.00014648435171693563,
190
- -0.00030273437732830644,
191
- 0.000195312371943146,
192
- 0.0009374999208375812,
193
- -0.001025390694849193,
 
 
 
 
 
194
  -0.00016601569950580597,
195
- 0.0001269530621357262,
196
- -0.0009179687476716936,
197
- -0.0034179689828306437
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
  ],
199
  "test_losses": [
200
- -0.1089999999999999,
201
- -0.10019999999999994,
202
- 0.014400000000000177,
203
- -0.011999999999999855,
204
- -0.09799999999999988,
205
- -0.052799999999999896,
206
- -0.3045999999999999,
207
- -0.2143999999999999,
208
- -0.13059999999999988,
209
- -0.06639999999999985,
210
- -0.07359999999999987,
211
- -0.18859999999999993,
212
- -0.03379999999999989,
213
- -0.1427999999999999,
214
- -0.09119999999999986,
215
- -0.12439999999999989,
216
- -0.373,
217
- -0.33019999999999994,
218
- -0.15339999999999987
219
  ],
220
  "config": {
221
  "training_type": "online_ppo",
222
- "environment": "MiniHack-Room-Random-15x15-v0",
223
  "total_timesteps": 195,
224
- "training_time": 3925.5714194774628,
225
  "device": "cuda",
226
  "ppo_config": {
227
  "learning_rate": 0.0003,
@@ -237,20 +237,20 @@
237
  "curiosity_skill_entropy": false,
238
  "curiosity_skill_transition_novelty": false,
239
  "curiosity_dyn_coef": 0.03,
240
- "curiosity_hdp_coef": 0.002,
241
- "curiosity_stn_coef": 0.0005,
242
  "use_rnd": true,
243
  "rnd_lr": 0.001,
244
  "rnd_coef": 0.002
245
  },
246
  "model_sources": {
247
- "vae_repo_id": "CatkinChen/nethack-vae-hmm",
248
- "hmm_repo_id": "CatkinChen/nethack-hmm"
249
  }
250
  },
251
- "final_train_loss": -0.0034179689828306437,
252
- "final_test_loss": -0.15339999999999987,
253
  "total_epochs": 195,
254
- "best_train_loss": -0.006171875633299351,
255
- "best_test_loss": -0.373
256
  }
 
1
  {
2
  "train_losses": [
3
+ 0.0003613280423451215,
4
+ 0.0011523436987772584,
5
+ 7.812489639036357e-05,
6
+ 0.0008105469169095159,
7
+ -6.835948443040252e-05,
8
+ 0.0010058593470603228,
9
+ -0.00010742194717749953,
10
+ -0.00013671873603016138,
11
+ -0.0021679687779396772,
12
+ 0.0005371093284338713,
13
+ 4.882807843387127e-05,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  -0.002119140699505806,
15
+ 0.0011035155039280653,
16
+ 0.0008300781482830644,
17
+ -0.0007128907018341124,
18
+ 5.859363591298461e-05,
19
+ 0.00020507792942225933,
20
+ -0.002080078236758709,
21
+ -0.0001171876210719347,
22
+ -0.0001367187942378223,
23
+ -0.00033203139901161194,
24
+ -0.000898437574505806,
25
+ -0.0005957031971774995,
26
+ -0.0028808596543967724,
27
+ 0.0001269530621357262,
28
+ 0.0009277343051508069,
29
+ 0.001748046837747097,
30
+ -0.00327148474752903,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  -0.0008886720170266926,
32
+ -0.0009374999790452421,
33
+ 0.00028320305864326656,
34
+ -0.0006445314502343535,
35
+ -0.001103515736758709,
36
+ -0.001679687760770321,
37
+ -0.0016015628352761269,
38
+ 0.0008691406110301614,
39
+ -0.002128906548023224,
40
+ 0.0008789062267169356,
41
+ 0.000732421875,
42
+ 0.0007812499534338713,
43
+ -0.001230468973517418,
44
+ -0.0017773439176380634,
45
+ 0.0009277343051508069,
46
+ -0.002490234561264515,
47
+ -0.00019531260477378964,
48
+ -0.0016992189921438694,
49
+ 0.00021484363242052495,
50
+ -0.00030273443553596735,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  -0.00018554690177552402,
52
+ -0.0010156250791624188,
53
+ -0.0002148438652511686,
54
+ -0.00023437506752088666,
55
+ 6.835925159975886e-05,
56
+ 0.0003124999348074198,
57
+ -0.0009277344215661287,
58
+ -0.000859375053551048,
59
+ 0.000849609321448952,
60
+ -3.9062462747097015e-05,
61
+ -0.0006054687546566129,
62
+ -0.0015429689083248377,
63
+ -0.0008496094960719347,
64
+ -0.0037011723034083843,
65
+ -3.9062550058588386e-05,
66
+ 0.0005078123649582267,
67
+ 0.00014648429350927472,
68
+ -0.0004101564409211278,
69
+ -0.0008300781482830644,
70
+ -0.0011914062779396772,
71
+ -0.001718750107102096,
72
+ 0.0001269530621357262,
73
+ -8.789071580395103e-05,
74
+ 0.00041992179467342794,
75
+ -0.0028417969588190317,
76
+ 0.0008789062267169356,
77
+ 0.0008593749371357262,
78
+ 0.0001855467853602022,
79
+ -0.0018066407646983862,
80
+ -0.0006738282972946763,
81
+ 0.00026367176906205714,
82
+ -0.0031542968936264515,
83
+ -0.0021386719308793545,
84
+ -0.0013183595146983862,
85
+ 0.0006738281226716936,
86
+ -0.0010937501210719347,
87
+ 0.0004980468656867743,
88
+ 0.001416015555150807,
89
+ -0.00017578131519258022,
90
+ -0.0011425783159211278,
91
+ 0.0005566406180150807,
92
+ -0.00024414071231149137,
93
+ -0.001914062537252903,
94
+ -0.0026953124906867743,
95
+ -0.000820312590803951,
96
+ 0.00038085930282250047,
97
  1.9531144062057137e-05,
98
+ -0.0012011720100417733,
99
+ 0.001015624962747097,
100
+ -0.0006835939711891115,
101
+ 0.0010058593470603228,
102
+ 0.00031249987659975886,
103
+ -0.002109374850988388,
104
+ -1.9531260477378964e-05,
105
+ 0.0009082030737772584,
106
+ 0.0007617187220603228,
107
+ 0.0008203124161809683,
108
+ 0.00039062497671693563,
109
+ -0.0006250001024454832,
110
+ -0.0010058593470603228,
111
+ -0.00030273443553596735,
112
+ 0.0006640624487772584,
113
+ -0.0010058593470603228,
114
+ -0.00046874998952262104,
115
  -0.00016601569950580597,
116
+ -0.0010351561941206455,
117
+ -0.002392577938735485,
118
+ -0.00025390629889443517,
119
+ 0.0002636718563735485,
120
+ 0.0002929687616415322,
121
+ 0.000283203087747097,
122
+ 0.00016601562674622983,
123
+ 0.0002734375011641532,
124
+ -0.000615234486758709,
125
+ -0.0010546875419095159,
126
+ 0.00023437495110556483,
127
+ -0.00024414071231149137,
128
+ 0.0006249999860301614,
129
+ -0.0004199219401925802,
130
+ -0.0003125000512227416,
131
+ -0.0006249999860301614,
132
+ 0.00041992185288108885,
133
+ -0.002695312723517418,
134
+ -0.005576171912252903,
135
+ -0.0020605470053851604,
136
+ 0.0007910155691206455,
137
+ -0.0032324218191206455,
138
+ -0.003095703199505806,
139
+ 0.0006445312174037099,
140
+ 0.00048828122089616954,
141
+ -0.001220703125,
142
+ -3.906257916241884e-05,
143
+ -0.0013183595146983862,
144
+ -0.0004003906506113708,
145
+ 0.0004101562371943146,
146
+ -0.0011230469681322575,
147
+ 0.0005371093284338713,
148
+ -0.00010742188896983862,
149
+ -0.005966797471046448,
150
+ -0.000244140625,
151
+ -0.0005664062337018549,
152
+ -0.0023828125558793545,
153
+ 0.0005078124813735485,
154
+ -0.002197265625,
155
+ -0.0010742186568677425,
156
+ -0.0021386719308793545,
157
+ 0.00044921872904524207,
158
+ -0.00036132821696810424,
159
+ -0.0004589843738358468,
160
+ -0.0002343750384170562,
161
+ -0.00020507816225290298,
162
+ -0.0001367187942378223,
163
+ 0.0006738281226716936,
164
+ 0.00048828122089616954,
165
+ 0.00041992185288108885,
166
+ -0.0004199218819849193,
167
+ 0.0005468750023283064,
168
+ -0.004150390625,
169
+ 0.0004003905924037099,
170
+ 9.765624417923391e-05,
171
+ 0.00020507810404524207,
172
+ -0.002236328087747097,
173
+ -0.0004199218819849193,
174
+ -0.0005371095612645149,
175
+ 4.8828194849193096e-05,
176
+ 0.0002441405667923391,
177
+ -0.002246093936264515,
178
+ 0.0003320312243886292,
179
+ -0.00012695312034338713,
180
+ -0.0020703128539025784,
181
+ -0.003310547210276127,
182
+ -0.0010449220426380634,
183
+ -0.0006250001024454832,
184
+ 0.00034179684007540345,
185
+ 0.0008789062267169356,
186
+ -2.929696347564459e-05,
187
+ 0.00025390624068677425,
188
+ 0.00032226560870185494,
189
+ -0.0021875002421438694,
190
+ -0.0004980469821020961,
191
+ 0.0003320312243886292,
192
+ -0.0008984376909211278,
193
+ -0.0006738281808793545,
194
+ -0.0010156251955777407,
195
+ -0.00011718765017576516,
196
+ -0.003017578274011612,
197
+ -0.0013671875931322575
198
  ],
199
  "test_losses": [
200
+ -0.33519999999999983,
201
+ -0.1731999999999999,
202
+ -0.0009999999999998404,
203
+ -0.07839999999999994,
204
+ -0.2763999999999999,
205
+ -0.2005999999999999,
206
+ -0.07279999999999989,
207
+ -0.10079999999999996,
208
+ -0.07419999999999993,
209
+ 0.00020000000000011453,
210
+ -0.22099999999999997,
211
+ -0.15119999999999995,
212
+ -0.25819999999999993,
213
+ -0.2673999999999999,
214
+ -0.2437999999999999,
215
+ -0.22659999999999997,
216
+ -0.2699999999999999,
217
+ -0.24459999999999998,
218
+ -0.16359999999999997
219
  ],
220
  "config": {
221
  "training_type": "online_ppo",
222
+ "environment": "MiniHack-River-Narrow-v0",
223
  "total_timesteps": 195,
224
+ "training_time": 5415.230568885803,
225
  "device": "cuda",
226
  "ppo_config": {
227
  "learning_rate": 0.0003,
 
237
  "curiosity_skill_entropy": false,
238
  "curiosity_skill_transition_novelty": false,
239
  "curiosity_dyn_coef": 0.03,
240
+ "curiosity_hdp_coef": 0.2,
241
+ "curiosity_stn_coef": 0.05,
242
  "use_rnd": true,
243
  "rnd_lr": 0.001,
244
  "rnd_coef": 0.002
245
  },
246
  "model_sources": {
247
+ "vae_repo_id": null,
248
+ "hmm_repo_id": null
249
  }
250
  },
251
+ "final_train_loss": -0.0013671875931322575,
252
+ "final_test_loss": -0.16359999999999997,
253
  "total_epochs": 195,
254
+ "best_train_loss": -0.005966797471046448,
255
+ "best_test_loss": -0.33519999999999983
256
  }