poca-SoccerTwos / run_logs /timers.json
dbaibak's picture
First Push / 11170000 steps
9218307
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.5817396640777588,
"min": 1.455094575881958,
"max": 3.295758008956909,
"count": 1117
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 29357.087890625,
"min": 20119.16796875,
"max": 114796.1875,
"count": 1117
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 52.795698924731184,
"min": 41.78632478632478,
"max": 999.0,
"count": 1117
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19640.0,
"min": 14576.0,
"max": 25692.0,
"count": 1117
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1617.6406867369267,
"min": 1199.9802019082556,
"max": 1639.294376297447,
"count": 1110
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 300881.16773306835,
"min": 2407.8869932951948,
"max": 375980.1001040295,
"count": 1110
},
"SoccerTwos.Step.mean": {
"value": 11169994.0,
"min": 9864.0,
"max": 11169994.0,
"count": 1117
},
"SoccerTwos.Step.sum": {
"value": 11169994.0,
"min": 9864.0,
"max": 11169994.0,
"count": 1117
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0189067330211401,
"min": -0.10604812204837799,
"max": 0.17163971066474915,
"count": 1117
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -3.4977455139160156,
"min": -20.073341369628906,
"max": 32.61154556274414,
"count": 1117
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.014979016967117786,
"min": -0.10466466844081879,
"max": 0.1675061136484146,
"count": 1117
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.7711181640625,
"min": -19.67367935180664,
"max": 31.826160430908203,
"count": 1117
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1117
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1117
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.040820540286399226,
"min": -0.4907428537096296,
"max": 0.5533685423015209,
"count": 1117
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -7.551799952983856,
"min": -68.55279970169067,
"max": 51.44579952955246,
"count": 1117
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.040820540286399226,
"min": -0.4907428537096296,
"max": 0.5533685423015209,
"count": 1117
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -7.551799952983856,
"min": -68.55279970169067,
"max": 51.44579952955246,
"count": 1117
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1117
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1117
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.015818389842752367,
"min": 0.01056509285311525,
"max": 0.023983135318849234,
"count": 540
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015818389842752367,
"min": 0.01056509285311525,
"max": 0.023983135318849234,
"count": 540
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.1106756404042244,
"min": 0.00010585838147865918,
"max": 0.12311240409811337,
"count": 540
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.1106756404042244,
"min": 0.00010585838147865918,
"max": 0.12311240409811337,
"count": 540
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.11272074555357298,
"min": 0.00010605515211257929,
"max": 0.12526631702979404,
"count": 540
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.11272074555357298,
"min": 0.00010605515211257929,
"max": 0.12526631702979404,
"count": 540
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 540
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 540
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 540
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 540
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 540
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 540
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675767301",
"python_version": "3.8.15 | packaged by conda-forge | (default, Nov 22 2022, 08:49:35) \n[GCC 10.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env=ml-agents/training-envs-executables/SoccerTwos.exe --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": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1675797412"
},
"total": 30110.425812047004,
"count": 1,
"self": 0.024434594000922516,
"children": {
"run_training.setup": {
"total": 0.017229047999990144,
"count": 1,
"self": 0.017229047999990144
},
"TrainerController.start_learning": {
"total": 30110.384148405003,
"count": 1,
"self": 24.077285353967454,
"children": {
"TrainerController._reset_env": {
"total": 6.759301012999913,
"count": 56,
"self": 6.759301012999913
},
"TrainerController.advance": {
"total": 30078.937422030034,
"count": 768718,
"self": 25.25196177511316,
"children": {
"env_step": {
"total": 22809.44976557272,
"count": 768718,
"self": 17891.032676758594,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4903.552269231004,
"count": 768718,
"self": 142.58574983506878,
"children": {
"TorchPolicy.evaluate": {
"total": 4760.966519395935,
"count": 1405796,
"self": 4760.966519395935
}
}
},
"workers": {
"total": 14.864819583121061,
"count": 768717,
"self": 0.0,
"children": {
"worker_root": {
"total": 30046.03928236312,
"count": 768717,
"is_parallel": true,
"self": 15095.742846892175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0046049020002101315,
"count": 2,
"is_parallel": true,
"self": 0.0013496899991878308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0032552120010223007,
"count": 8,
"is_parallel": true,
"self": 0.0032552120010223007
}
}
},
"UnityEnvironment.step": {
"total": 0.039663079000092694,
"count": 1,
"is_parallel": true,
"self": 0.001042876999690634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009266420001949882,
"count": 1,
"is_parallel": true,
"self": 0.0009266420001949882
},
"communicator.exchange": {
"total": 0.034336171000177274,
"count": 1,
"is_parallel": true,
"self": 0.034336171000177274
},
"steps_from_proto": {
"total": 0.003357389000029798,
"count": 2,
"is_parallel": true,
"self": 0.0006177839991323708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002739605000897427,
"count": 8,
"is_parallel": true,
"self": 0.002739605000897427
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 14950.139402001958,
"count": 768716,
"is_parallel": true,
"self": 810.3926871098065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 581.4884008703025,
"count": 768716,
"is_parallel": true,
"self": 581.4884008703025
},
"communicator.exchange": {
"total": 10917.931029128304,
"count": 768716,
"is_parallel": true,
"self": 10917.931029128304
},
"steps_from_proto": {
"total": 2640.3272848935453,
"count": 1537432,
"is_parallel": true,
"self": 493.16249945778736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2147.164785435758,
"count": 6149728,
"is_parallel": true,
"self": 2147.164785435758
}
}
}
}
},
"steps_from_proto": {
"total": 0.15703346898544623,
"count": 110,
"is_parallel": true,
"self": 0.030603315996813762,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.12643015298863247,
"count": 440,
"is_parallel": true,
"self": 0.12643015298863247
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 7244.235694682202,
"count": 768717,
"self": 172.02504888342446,
"children": {
"process_trajectory": {
"total": 3104.2678107138054,
"count": 768717,
"self": 3097.6380572478156,
"children": {
"RLTrainer._checkpoint": {
"total": 6.629753465989779,
"count": 22,
"self": 6.629753465989779
}
}
},
"_update_policy": {
"total": 3967.9428350849716,
"count": 540,
"self": 2525.3373333656814,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1442.6055017192903,
"count": 16200,
"self": 1442.6055017192903
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4360048226080835e-06,
"count": 1,
"self": 1.4360048226080835e-06
},
"TrainerController._save_models": {
"total": 0.6101385719957761,
"count": 1,
"self": 0.0024646999954711646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.607673872000305,
"count": 1,
"self": 0.607673872000305
}
}
}
}
}
}
}