poca-SoccerTwos / run_logs /timers.json
Nake's picture
First Push`
3b1061d
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.025925636291504,
"min": 2.025925636291504,
"max": 3.2104034423828125,
"count": 524
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 39286.75,
"min": 13521.818359375,
"max": 116358.4296875,
"count": 524
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 57.38823529411765,
"min": 44.01801801801802,
"max": 999.0,
"count": 524
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19512.0,
"min": 1496.0,
"max": 27884.0,
"count": 524
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1532.0334634522876,
"min": 1195.0779705599898,
"max": 1535.7760924164031,
"count": 470
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 260445.6887868889,
"min": 2394.2350413266436,
"max": 334574.55590176454,
"count": 470
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 524
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 524
},
"SoccerTwos.Step.mean": {
"value": 5729936.0,
"min": 509227.0,
"max": 5729936.0,
"count": 523
},
"SoccerTwos.Step.sum": {
"value": 5729936.0,
"min": 509227.0,
"max": 5729936.0,
"count": 523
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.030392160639166832,
"min": -0.0822305753827095,
"max": 0.17004992067813873,
"count": 523
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 5.166667461395264,
"min": -14.984886169433594,
"max": 25.32577133178711,
"count": 523
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.028856055811047554,
"min": -0.07947594672441483,
"max": 0.1721847653388977,
"count": 523
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 4.905529499053955,
"min": -14.787622451782227,
"max": 25.734031677246094,
"count": 523
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 523
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 523
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.03752940963296329,
"min": -0.6,
"max": 0.4764734692111307,
"count": 523
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -6.37999963760376,
"min": -54.33399999141693,
"max": 61.91520017385483,
"count": 523
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.03752940963296329,
"min": -0.6,
"max": 0.4764734692111307,
"count": 523
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -6.37999963760376,
"min": -54.33399999141693,
"max": 61.91520017385483,
"count": 523
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.018134896001871917,
"min": 0.011531886000496646,
"max": 0.022692488355096428,
"count": 248
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.018134896001871917,
"min": 0.011531886000496646,
"max": 0.022692488355096428,
"count": 248
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10663323253393173,
"min": 1.2603006590931424e-07,
"max": 0.13087685033679008,
"count": 248
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10663323253393173,
"min": 1.2603006590931424e-07,
"max": 0.13087685033679008,
"count": 248
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.1092075044910113,
"min": 2.0802667629974773e-07,
"max": 0.1342946653564771,
"count": 248
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.1092075044910113,
"min": 2.0802667629974773e-07,
"max": 0.1342946653564771,
"count": 248
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 248
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 248
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 248
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 248
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 248
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 248
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1682000009",
"python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "D:\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.0+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1682026607"
},
"total": 26597.9878642,
"count": 1,
"self": 0.6744933999980276,
"children": {
"run_training.setup": {
"total": 0.1066562000000002,
"count": 1,
"self": 0.1066562000000002
},
"TrainerController.start_learning": {
"total": 26597.2067146,
"count": 1,
"self": 8.350169800411095,
"children": {
"TrainerController._reset_env": {
"total": 5.346938199993901,
"count": 28,
"self": 5.346938199993901
},
"TrainerController.advance": {
"total": 26583.347293599596,
"count": 351057,
"self": 8.558599800795491,
"children": {
"env_step": {
"total": 6229.705558499158,
"count": 351057,
"self": 4561.993204798748,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1661.9456900003395,
"count": 351057,
"self": 59.24428410067412,
"children": {
"TorchPolicy.evaluate": {
"total": 1602.7014058996654,
"count": 664772,
"self": 1602.7014058996654
}
}
},
"workers": {
"total": 5.766663700070358,
"count": 351057,
"self": 0.0,
"children": {
"worker_root": {
"total": 26580.71004499844,
"count": 351057,
"is_parallel": true,
"self": 23015.088176198915,
"children": {
"steps_from_proto": {
"total": 0.059993899994433164,
"count": 56,
"is_parallel": true,
"self": 0.011516499986582218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.048477400007850946,
"count": 224,
"is_parallel": true,
"self": 0.048477400007850946
}
}
},
"UnityEnvironment.step": {
"total": 3565.5618748995316,
"count": 351057,
"is_parallel": true,
"self": 217.03973039973835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 193.86752719954663,
"count": 351057,
"is_parallel": true,
"self": 193.86752719954663
},
"communicator.exchange": {
"total": 2476.8373721992566,
"count": 351057,
"is_parallel": true,
"self": 2476.8373721992566
},
"steps_from_proto": {
"total": 677.8172451009902,
"count": 702114,
"is_parallel": true,
"self": 132.6210061023652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 545.1962389986251,
"count": 2808456,
"is_parallel": true,
"self": 545.1962389986251
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 20345.083135299643,
"count": 351057,
"self": 61.57795450038611,
"children": {
"process_trajectory": {
"total": 2498.30639159926,
"count": 351057,
"self": 2496.4375071992577,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8688844000025728,
"count": 11,
"self": 1.8688844000025728
}
}
},
"_update_policy": {
"total": 17785.198789199996,
"count": 248,
"self": 1072.4896487000697,
"children": {
"TorchPOCAOptimizer.update": {
"total": 16712.709140499926,
"count": 7449,
"self": 16712.709140499926
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0000003385357559e-06,
"count": 1,
"self": 1.0000003385357559e-06
},
"TrainerController._save_models": {
"total": 0.1623120000003837,
"count": 1,
"self": 0.009103399999730755,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15320860000065295,
"count": 1,
"self": 0.15320860000065295
}
}
}
}
}
}
}