CatkinChen's picture
Add training data
d69eaf6 verified
{
"train_losses": [
0.001259765587747097,
0.0014453125186264515,
0.0009667968261055648,
0.0010839843889698386,
0.001054687425494194,
7.812492549419403e-05,
0.0010351561941206455,
8.78905993886292e-05,
0.0011425780830904841,
-0.0001855469890870154,
0.0011425780830904841,
-0.0007617187220603228,
-0.00400390662252903,
-0.000898437574505806,
-0.0021777343936264515,
-0.001757812686264515,
0.0008398437639698386,
-5.820766091346741e-11,
-0.0017675783019512892,
-0.0012792969355359674,
0.0002246092481072992,
-0.0008691407274454832,
0.00027343747206032276,
-0.001884765806607902,
-0.002216797089204192,
-0.0017480469541624188,
-0.0009765627328306437,
-0.0019628906156867743,
-0.0012402344727888703,
-0.0001660156704019755,
-0.0012597658205777407,
-0.001064453274011612,
-0.0005566407344304025,
0.0005078124231658876,
0.0008105469169095159,
-0.00023437506752088666,
-9.76564479060471e-06,
-0.004941406659781933,
-0.0018945313058793545,
-0.00038085944834165275,
-0.0011718750465661287,
-0.002128906548023224,
-0.0022656251676380634,
-0.0017285157227888703,
-0.004804687574505806,
-0.0012207032414153218,
0.0003710937453433871,
0.0003124999930150807,
-0.0008105469169095159,
-0.0007617188384756446,
-0.0008496093796566129,
0.0011328124674037099,
0.0011523438151925802,
-0.0029980470426380634,
-0.002216797089204192,
-0.0014453125186264515,
-0.0011718750465661287,
-0.0016699220286682248,
-0.0021484375465661287,
-0.002089843852445483,
-0.0008300782064907253,
-0.0016308595659211278,
-0.00013671882334165275,
0.00026367176906205714,
-0.0018652345752343535,
-0.0005859374650754035,
0.0005078124813735485,
-0.000449218787252903,
-0.004062500316649675,
0.0003808593610301614,
-0.0016992188757285476,
-0.001152343931607902,
-0.0014941407134756446,
-0.0003027344646397978,
-0.002050781389698386,
-0.0008398438221774995,
-0.00018554693087935448,
0.0008300780900754035,
0.00039062497671693563,
0.0004101562371943146,
-0.0005371094448491931,
0.0008300780900754035,
0.001416015555150807,
-0.0012597658205777407,
-0.002011718926951289,
-0.0005761719075962901,
-0.0004199218819849193,
0.0005078124813735485,
-0.00016601569950580597,
-0.0013769532088190317,
-0.001191406394354999,
0.0003320312243886292,
-0.0002734375884756446,
-0.0011230469681322575,
-0.00041992191108874977,
0.00042968749767169356,
0.0003124999930150807,
0.0009277343051508069,
-0.0012109375093132257,
-0.00017578131519258022,
-0.0023144534789025784,
-0.0012500002048909664,
0.0006445312174037099,
-0.0015527344075962901,
-0.0003808594774454832,
-0.0009277345379814506,
-0.0023046876303851604,
-0.00037109380355104804,
-0.0023144532460719347,
-0.001308593899011612,
-0.0016015626024454832,
-0.002089843852445483,
-0.00040039062150754035,
0.0007421874906867743,
-0.0010644531575962901,
-0.0002441406832076609,
-0.0007714845705777407,
-0.0013378907460719347,
-0.0005468750605359674,
0.0003906250058207661,
-0.0005468750605359674,
-0.0005371094448491931,
-0.0011718751629814506,
-1.9531347788870335e-05,
-7.812512922100723e-05,
-0.001591796986758709,
-0.0017089844914153218,
-0.0012109376257285476,
-0.0014257814036682248,
-0.0013183595146983862,
-0.002333984477445483,
-0.0012402344727888703,
-0.0004687500186264515,
-0.001513671944849193,
-0.0010156250791624188,
-0.0005175782134756446,
-0.00046875004773028195,
-0.0014453125186264515,
-0.00046875010593794286,
-0.0002929687325377017,
-0.00028320314595475793,
-0.0021972658578306437,
-0.0006835937965661287,
0.00028320311685092747,
-0.00020507816225290298,
-0.0016308595659211278,
-0.002089843852445483,
-0.002207031473517418,
-0.0005175782134756446,
-0.0004101563536096364,
-0.0015820313710719347,
3.906243364326656e-05,
-0.0015234375605359674,
-0.0013574219774454832,
-0.002246093936264515,
-0.00025390624068677425,
-0.0006835937383584678,
-0.002412109635770321,
-0.0037695313803851604,
-0.0015332032926380634,
-0.00032226572511717677,
-0.0014062500558793545,
-0.005273438058793545,
-0.0005175782716833055,
-0.0021386719308793545,
0.0003320312243886292,
-0.0009960939642041922,
-0.0030175780411809683,
-0.0009179689222946763,
-0.001923828269354999,
-0.001347656361758709,
0.0004003905924037099,
-0.0006152343703433871,
-0.0025976565666496754,
-0.003398437751457095,
-0.002285156399011612,
-0.0012792969355359674,
-0.002070312388241291,
-0.0002929688198491931,
0.0002929687325377017,
-0.0003515625139698386,
0.0004101562371943146,
-0.002646484412252903,
-0.003027343889698386,
-0.002216797089204192,
-0.0005761719075962901,
-2.9296876164153218e-05,
-0.0015332030598074198,
0.0004394531133584678,
-0.0003613281878642738,
-0.002080078236758709,
-0.002041015774011612,
-0.0002246094518341124,
0.000771484337747097,
-0.0003124999930150807
],
"test_losses": [
0.15960000000000016,
-0.19399999999999992,
-0.22579999999999995,
-0.17239999999999994,
-0.21659999999999993,
-0.10759999999999995,
-0.18059999999999996,
-0.17859999999999998,
-0.25699999999999995,
0.054400000000000046,
-0.37479999999999997,
-0.2975999999999999,
-0.15419999999999995,
-0.12619999999999995,
-0.17559999999999995,
-0.24759999999999993,
-0.15019999999999994,
-0.24239999999999995,
-0.3181999999999999
],
"config": {
"training_type": "online_ppo",
"environment": "MiniHack-River-Narrow-v0",
"total_timesteps": 195,
"training_time": 4517.042412281036,
"device": "cuda",
"ppo_config": {
"learning_rate": 0.0003,
"n_epochs": 4,
"gamma": 0.99,
"vf_coef": 0.5,
"ent_coef": 0.01,
"max_grad_norm": 0.5
},
"exploration_config": {
"use_curiosity": true,
"curiosity_dyn": true,
"curiosity_skill_entropy": true,
"curiosity_skill_transition_novelty": true,
"curiosity_dyn_coef": 0.03,
"curiosity_hdp_coef": 0.2,
"curiosity_stn_coef": 0.05,
"use_rnd": false,
"rnd_lr": null,
"rnd_coef": null
},
"model_sources": {
"vae_repo_id": null,
"hmm_repo_id": null
}
},
"final_train_loss": -0.0003124999930150807,
"final_test_loss": -0.3181999999999999,
"total_epochs": 195,
"best_train_loss": -0.005273438058793545,
"best_test_loss": -0.37479999999999997
}