sergey-antonov's picture
poca
118370c
raw
history blame contribute delete
No virus
20.1 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.597999930381775,
"min": 1.5763094425201416,
"max": 3.295719623565674,
"count": 1000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 32982.71875,
"min": 27483.0078125,
"max": 122891.171875,
"count": 1000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 57.51190476190476,
"min": 45.018181818181816,
"max": 999.0,
"count": 1000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19324.0,
"min": 10740.0,
"max": 29604.0,
"count": 1000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1578.4634818700745,
"min": 1198.0030185127453,
"max": 1578.8248305855498,
"count": 983
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 265181.8649541725,
"min": 2397.980086043466,
"max": 324736.06161352916,
"count": 983
},
"SoccerTwos.Step.mean": {
"value": 9999869.0,
"min": 9818.0,
"max": 9999869.0,
"count": 1000
},
"SoccerTwos.Step.sum": {
"value": 9999869.0,
"min": 9818.0,
"max": 9999869.0,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.008387032896280289,
"min": -0.11922935396432877,
"max": 0.14547722041606903,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.4174085855484009,
"min": -19.527896881103516,
"max": 21.373390197753906,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.011889728717505932,
"min": -0.1223214715719223,
"max": 0.14765849709510803,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.009364128112793,
"min": -19.650978088378906,
"max": 21.514358520507812,
"count": 1000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.029576331200684317,
"min": -0.7058823529411765,
"max": 0.4543714262545109,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 4.998399972915649,
"min": -57.091200053691864,
"max": 59.33999991416931,
"count": 1000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.029576331200684317,
"min": -0.7058823529411765,
"max": 0.4543714262545109,
"count": 1000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 4.998399972915649,
"min": -57.091200053691864,
"max": 59.33999991416931,
"count": 1000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.019821044598938898,
"min": 0.009762871229516653,
"max": 0.024478399419846635,
"count": 482
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.019821044598938898,
"min": 0.009762871229516653,
"max": 0.024478399419846635,
"count": 482
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09551407669981321,
"min": 2.653380576399892e-05,
"max": 0.11908974970380465,
"count": 482
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09551407669981321,
"min": 2.653380576399892e-05,
"max": 0.11908974970380465,
"count": 482
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09744785949587823,
"min": 2.6889112511222872e-05,
"max": 0.12114204168319702,
"count": 482
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09744785949587823,
"min": 2.6889112511222872e-05,
"max": 0.12114204168319702,
"count": 482
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 482
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 482
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 482
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 482
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 482
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 482
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676948853",
"python_version": "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]",
"command_line_arguments": "/home/hit/app/hf39/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos2 --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1",
"numpy_version": "1.21.2",
"end_time_seconds": "1676967976"
},
"total": 19123.076667693997,
"count": 1,
"self": 0.21990420399379218,
"children": {
"run_training.setup": {
"total": 0.007959242999277194,
"count": 1,
"self": 0.007959242999277194
},
"TrainerController.start_learning": {
"total": 19122.848804247005,
"count": 1,
"self": 10.1721016821175,
"children": {
"TrainerController._reset_env": {
"total": 1.3919247640005779,
"count": 50,
"self": 1.3919247640005779
},
"TrainerController.advance": {
"total": 19111.117977610884,
"count": 683845,
"self": 9.492940464398998,
"children": {
"env_step": {
"total": 9450.683740710707,
"count": 683845,
"self": 8185.751511323773,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1258.853748303307,
"count": 683845,
"self": 49.26352578895603,
"children": {
"TorchPolicy.evaluate": {
"total": 1209.590222514351,
"count": 1258710,
"self": 1209.590222514351
}
}
},
"workers": {
"total": 6.078481083626684,
"count": 683845,
"self": 0.0,
"children": {
"worker_root": {
"total": 19106.2428700923,
"count": 683845,
"is_parallel": true,
"self": 12086.115747789616,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0037094389990670606,
"count": 2,
"is_parallel": true,
"self": 0.000757171996156103,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029522670029109577,
"count": 8,
"is_parallel": true,
"self": 0.0029522670029109577
}
}
},
"UnityEnvironment.step": {
"total": 0.02006031899873051,
"count": 1,
"is_parallel": true,
"self": 0.0010297060016455362,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006962979987292783,
"count": 1,
"is_parallel": true,
"self": 0.0006962979987292783
},
"communicator.exchange": {
"total": 0.01564516299913521,
"count": 1,
"is_parallel": true,
"self": 0.01564516299913521
},
"steps_from_proto": {
"total": 0.002689151999220485,
"count": 2,
"is_parallel": true,
"self": 0.00046761899648117833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022215330027393065,
"count": 8,
"is_parallel": true,
"self": 0.0022215330027393065
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 7020.015793536695,
"count": 683844,
"is_parallel": true,
"self": 512.6880163747483,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 327.6017931244969,
"count": 683844,
"is_parallel": true,
"self": 327.6017931244969
},
"communicator.exchange": {
"total": 4865.338903257993,
"count": 683844,
"is_parallel": true,
"self": 4865.338903257993
},
"steps_from_proto": {
"total": 1314.3870807794574,
"count": 1367688,
"is_parallel": true,
"self": 214.04279505178056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1100.3442857276768,
"count": 5470752,
"is_parallel": true,
"self": 1100.3442857276768
}
}
}
}
},
"steps_from_proto": {
"total": 0.11132876599003794,
"count": 98,
"is_parallel": true,
"self": 0.017943563985681976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.09338520200435596,
"count": 392,
"is_parallel": true,
"self": 0.09338520200435596
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 9650.941296435776,
"count": 683845,
"self": 75.88202906467086,
"children": {
"process_trajectory": {
"total": 1640.6616224380905,
"count": 683845,
"self": 1637.2550899631005,
"children": {
"RLTrainer._checkpoint": {
"total": 3.4065324749899446,
"count": 20,
"self": 3.4065324749899446
}
}
},
"_update_policy": {
"total": 7934.397644933015,
"count": 482,
"self": 1233.889028515081,
"children": {
"TorchPOCAOptimizer.update": {
"total": 6700.508616417934,
"count": 14475,
"self": 6700.508616417934
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.710026016458869e-07,
"count": 1,
"self": 5.710026016458869e-07
},
"TrainerController._save_models": {
"total": 0.16679961900081253,
"count": 1,
"self": 0.006717814001603983,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16008180499920854,
"count": 1,
"self": 0.16008180499920854
}
}
}
}
}
}
}