nomad-ai's picture
First Push
071ae7c
raw
history blame
20.3 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.3107171058654785,
"min": 1.2835277318954468,
"max": 3.2957358360290527,
"count": 2000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 26927.37109375,
"min": 9702.64453125,
"max": 114557.84375,
"count": 2000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 104.7872340425532,
"min": 55.689655172413794,
"max": 999.0,
"count": 2000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19700.0,
"min": 4188.0,
"max": 31432.0,
"count": 2000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1509.3954662816727,
"min": 1200.7492804441454,
"max": 1551.0129319287528,
"count": 1958
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 141883.17383047723,
"min": 2401.4985608882907,
"max": 257794.0168510954,
"count": 1958
},
"SoccerTwos.Step.mean": {
"value": 19999900.0,
"min": 9732.0,
"max": 19999900.0,
"count": 2000
},
"SoccerTwos.Step.sum": {
"value": 19999900.0,
"min": 9732.0,
"max": 19999900.0,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.04351792484521866,
"min": -0.12536892294883728,
"max": 0.14809076488018036,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -4.09068489074707,
"min": -17.77437400817871,
"max": 20.666837692260742,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05282298102974892,
"min": -0.14034530520439148,
"max": 0.19755327701568604,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -4.965360164642334,
"min": -21.092086791992188,
"max": 22.521074295043945,
"count": 2000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 2000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.1741638310412143,
"min": -0.5138399988412857,
"max": 0.39311765134334564,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -16.371400117874146,
"min": -56.02159994840622,
"max": 48.17599952220917,
"count": 2000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.1741638310412143,
"min": -0.5138399988412857,
"max": 0.39311765134334564,
"count": 2000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -16.371400117874146,
"min": -56.02159994840622,
"max": 48.17599952220917,
"count": 2000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.044109163780231025,
"min": 0.01052496551474178,
"max": 0.044761698539950885,
"count": 485
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.044109163780231025,
"min": 0.01052496551474178,
"max": 0.044761698539950885,
"count": 485
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.03855889186263085,
"min": 6.812689679463801e-05,
"max": 0.19760399928083644,
"count": 485
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.03855889186263085,
"min": 6.812689679463801e-05,
"max": 0.19760399928083644,
"count": 485
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.05349807057529688,
"min": 0.00011392231601348613,
"max": 1.1345150957867736,
"count": 485
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.05349807057529688,
"min": 0.00011392231601348613,
"max": 1.1345150957867736,
"count": 485
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003500000000000001,
"min": 0.0003500000000000001,
"max": 0.0003500000000000001,
"count": 485
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003500000000000001,
"min": 0.0003500000000000001,
"max": 0.0003500000000000001,
"count": 485
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.19999999999999996,
"min": 0.19999999999999996,
"max": 0.19999999999999996,
"count": 485
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.19999999999999996,
"min": 0.19999999999999996,
"max": 0.19999999999999996,
"count": 485
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.004999999999999999,
"min": 0.004999999999999999,
"max": 0.004999999999999999,
"count": 485
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.004999999999999999,
"min": 0.004999999999999999,
"max": 0.004999999999999999,
"count": 485
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691939930",
"python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]",
"command_line_arguments": "/root/anaconda3/envs/audio/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692303525"
},
"total": 363595.147505951,
"count": 1,
"self": 0.22522742598084733,
"children": {
"run_training.setup": {
"total": 0.017680066000025363,
"count": 1,
"self": 0.017680066000025363
},
"TrainerController.start_learning": {
"total": 363594.904598459,
"count": 1,
"self": 29.56684974685777,
"children": {
"TrainerController._reset_env": {
"total": 3.076185627792256,
"count": 100,
"self": 3.076185627792256
},
"TrainerController.advance": {
"total": 363561.78595752735,
"count": 1344648,
"self": 27.944567902944982,
"children": {
"env_step": {
"total": 21792.674879346883,
"count": 1344648,
"self": 17040.027073295787,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4736.125254615943,
"count": 1344648,
"self": 143.8249484822536,
"children": {
"TorchPolicy.evaluate": {
"total": 4592.300306133689,
"count": 2519436,
"self": 4592.300306133689
}
}
},
"workers": {
"total": 16.52255143515515,
"count": 1344648,
"self": 0.0,
"children": {
"worker_root": {
"total": 363545.56482978526,
"count": 1344648,
"is_parallel": true,
"self": 349505.0382856348,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031931590000340293,
"count": 2,
"is_parallel": true,
"self": 0.001613930000075925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015792289999581044,
"count": 8,
"is_parallel": true,
"self": 0.0015792289999581044
}
}
},
"UnityEnvironment.step": {
"total": 0.03475630299999466,
"count": 1,
"is_parallel": true,
"self": 0.0009333209999340397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007283090000100856,
"count": 1,
"is_parallel": true,
"self": 0.0007283090000100856
},
"communicator.exchange": {
"total": 0.030483814000035636,
"count": 1,
"is_parallel": true,
"self": 0.030483814000035636
},
"steps_from_proto": {
"total": 0.002610859000014898,
"count": 2,
"is_parallel": true,
"self": 0.0004920599999422848,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002118799000072613,
"count": 8,
"is_parallel": true,
"self": 0.002118799000072613
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 14040.374241508705,
"count": 1344647,
"is_parallel": true,
"self": 669.6697867685598,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 560.0612583518777,
"count": 1344647,
"is_parallel": true,
"self": 560.0612583518777
},
"communicator.exchange": {
"total": 10863.667504166358,
"count": 1344647,
"is_parallel": true,
"self": 10863.667504166358
},
"steps_from_proto": {
"total": 1946.9756922219092,
"count": 2689294,
"is_parallel": true,
"self": 374.13589754678856,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1572.8397946751206,
"count": 10757176,
"is_parallel": true,
"self": 1572.8397946751206
}
}
}
}
},
"steps_from_proto": {
"total": 0.15230264180354425,
"count": 198,
"is_parallel": true,
"self": 0.03053507476897721,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.12176756703456704,
"count": 792,
"is_parallel": true,
"self": 0.12176756703456704
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 341741.16651027754,
"count": 1344648,
"self": 227.45613102888456,
"children": {
"process_trajectory": {
"total": 12143.364268319947,
"count": 1344648,
"self": 12122.029537628841,
"children": {
"RLTrainer._checkpoint": {
"total": 21.334730691105506,
"count": 40,
"self": 21.334730691105506
}
}
},
"_update_policy": {
"total": 329370.3461109287,
"count": 485,
"self": 8145.140302237065,
"children": {
"TorchPOCAOptimizer.update": {
"total": 321225.2058086916,
"count": 48500,
"self": 321225.2058086916
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.200295269489288e-07,
"count": 1,
"self": 8.200295269489288e-07
},
"TrainerController._save_models": {
"total": 0.4756047370028682,
"count": 1,
"self": 0.003126650000922382,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4724780870019458,
"count": 1,
"self": 0.4724780870019458
}
}
}
}
}
}
}