poca-SoccerTwos / run_logs /timers.json
Sam017's picture
First Push`
a54792f verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.4964483976364136,
"min": 1.4605510234832764,
"max": 1.5155034065246582,
"count": 176
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 30647.263671875,
"min": 24965.033203125,
"max": 36760.4609375,
"count": 176
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 105.80851063829788,
"min": 59.975,
"max": 121.14634146341463,
"count": 176
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19892.0,
"min": 17816.0,
"max": 21640.0,
"count": 176
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1754.295554608228,
"min": 1705.440247019905,
"max": 1788.2708276739409,
"count": 176
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 164903.78213317343,
"min": 140197.75672877918,
"max": 277546.6218702038,
"count": 176
},
"SoccerTwos.Step.mean": {
"value": 29999878.0,
"min": 28249968.0,
"max": 29999878.0,
"count": 176
},
"SoccerTwos.Step.sum": {
"value": 29999878.0,
"min": 28249968.0,
"max": 29999878.0,
"count": 176
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.08596646785736084,
"min": -0.11127919703722,
"max": 0.05069214850664139,
"count": 176
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -8.08084774017334,
"min": -15.755184173583984,
"max": 5.778904914855957,
"count": 176
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.08620979636907578,
"min": -0.11121446639299393,
"max": 0.05157194659113884,
"count": 176
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -8.103720664978027,
"min": -15.609806060791016,
"max": 5.879201889038086,
"count": 176
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 176
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 176
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.3159276614797876,
"min": -0.3918128451076123,
"max": 0.3059328455124458,
"count": 176
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -29.697200179100037,
"min": -42.707600116729736,
"max": 41.91279983520508,
"count": 176
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.3159276614797876,
"min": -0.3918128451076123,
"max": 0.3059328455124458,
"count": 176
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -29.697200179100037,
"min": -42.707600116729736,
"max": 41.91279983520508,
"count": 176
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 176
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 176
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.025743399398197652,
"min": 0.024931373610161244,
"max": 0.028063555206172167,
"count": 42
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.025743399398197652,
"min": 0.024931373610161244,
"max": 0.028063555206172167,
"count": 42
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0752385701239109,
"min": 0.07482468090951443,
"max": 0.08802365750074387,
"count": 42
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0752385701239109,
"min": 0.07482468090951443,
"max": 0.08802365750074387,
"count": 42
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.07908420950174332,
"min": 0.07774422004818916,
"max": 0.09233857527375221,
"count": 42
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.07908420950174332,
"min": 0.07774422004818916,
"max": 0.09233857527375221,
"count": 42
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 42
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 42
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.19999999999999996,
"min": 0.19999999999999996,
"max": 0.19999999999999996,
"count": 42
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.19999999999999996,
"min": 0.19999999999999996,
"max": 0.19999999999999996,
"count": 42
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 42
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 42
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750675981",
"python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\Samuele\\PycharmProjects\\HF_Deep_RL_Course\\7_multi_agents_ai_vs_ai\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1750679163"
},
"total": 3182.5345012999605,
"count": 1,
"self": 0.23923559999093413,
"children": {
"run_training.setup": {
"total": 0.13439429993741214,
"count": 1,
"self": 0.13439429993741214
},
"TrainerController.start_learning": {
"total": 3182.160871400032,
"count": 1,
"self": 2.036284110392444,
"children": {
"TrainerController._reset_env": {
"total": 5.648444600170478,
"count": 19,
"self": 5.648444600170478
},
"TrainerController.advance": {
"total": 3174.283332989551,
"count": 119624,
"self": 1.791399484849535,
"children": {
"env_step": {
"total": 2231.455010698759,
"count": 119624,
"self": 1284.315249469597,
"children": {
"SubprocessEnvManager._take_step": {
"total": 945.788599017309,
"count": 119624,
"self": 11.467191099189222,
"children": {
"TorchPolicy.evaluate": {
"total": 934.3214079181198,
"count": 222070,
"self": 934.3214079181198
}
}
},
"workers": {
"total": 1.3511622118530795,
"count": 119624,
"self": 0.0,
"children": {
"worker_root": {
"total": 3175.001966870972,
"count": 119624,
"is_parallel": true,
"self": 2125.1288221523864,
"children": {
"steps_from_proto": {
"total": 0.02838729997165501,
"count": 38,
"is_parallel": true,
"self": 0.0046572997234761715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.02373000024817884,
"count": 152,
"is_parallel": true,
"self": 0.02373000024817884
}
}
},
"UnityEnvironment.step": {
"total": 1049.8447574186139,
"count": 119624,
"is_parallel": true,
"self": 54.86154952063225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 42.58077939366922,
"count": 119624,
"is_parallel": true,
"self": 42.58077939366922
},
"communicator.exchange": {
"total": 774.1797251862008,
"count": 119624,
"is_parallel": true,
"self": 774.1797251862008
},
"steps_from_proto": {
"total": 178.2227033181116,
"count": 239248,
"is_parallel": true,
"self": 29.4276036079973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 148.7950997101143,
"count": 956992,
"is_parallel": true,
"self": 148.7950997101143
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 941.0369228059426,
"count": 119624,
"self": 15.35098659596406,
"children": {
"process_trajectory": {
"total": 424.54034440987743,
"count": 119624,
"self": 423.7169448098866,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8233995999908075,
"count": 4,
"self": 0.8233995999908075
}
}
},
"_update_policy": {
"total": 501.1455918001011,
"count": 42,
"self": 306.84472250018734,
"children": {
"TorchPOCAOptimizer.update": {
"total": 194.30086929991376,
"count": 2100,
"self": 194.30086929991376
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.00005330145359e-07,
"count": 1,
"self": 7.00005330145359e-07
},
"TrainerController._save_models": {
"total": 0.1928089999128133,
"count": 1,
"self": 0.009940099902451038,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18286890001036227,
"count": 1,
"self": 0.18286890001036227
}
}
}
}
}
}
}