dp15's picture
first Push
45f463f
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.274477243423462,
"min": 3.2512295246124268,
"max": 3.2958054542541504,
"count": 800
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 38036.328125,
"min": 7712.3486328125,
"max": 155451.140625,
"count": 800
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 701.0,
"min": 370.84615384615387,
"max": 999.0,
"count": 800
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19628.0,
"min": 16152.0,
"max": 23784.0,
"count": 800
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1219.212509345193,
"min": 1171.4763390070757,
"max": 1223.2151618217388,
"count": 707
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 7315.275056071157,
"min": 2343.5345128418494,
"max": 21357.008077002094,
"count": 707
},
"SoccerTwos.Step.mean": {
"value": 7999862.0,
"min": 9965.0,
"max": 7999862.0,
"count": 800
},
"SoccerTwos.Step.sum": {
"value": 7999862.0,
"min": 9965.0,
"max": 7999862.0,
"count": 800
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.003647875739261508,
"min": -0.009167383424937725,
"max": 0.011413229629397392,
"count": 800
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.05471813678741455,
"min": -0.11642808467149734,
"max": 0.19402490556240082,
"count": 800
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0027940995059907436,
"min": -0.01826617680490017,
"max": 0.011413218453526497,
"count": 800
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.041911493986845016,
"min": -0.4395439624786377,
"max": 0.1940246820449829,
"count": 800
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 800
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 800
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.22357333501180013,
"min": -0.7142857142857143,
"max": 0.3778500035405159,
"count": 800
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -3.353600025177002,
"min": -11.220400005578995,
"max": 6.751000016927719,
"count": 800
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.22357333501180013,
"min": -0.7142857142857143,
"max": 0.3778500035405159,
"count": 800
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -3.353600025177002,
"min": -11.220400005578995,
"max": 6.751000016927719,
"count": 800
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 800
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 800
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01781478886754485,
"min": 0.011520216083736158,
"max": 0.02296207548264647,
"count": 374
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01781478886754485,
"min": 0.011520216083736158,
"max": 0.02296207548264647,
"count": 374
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.001419035327853635,
"min": 1.8255413092305162e-07,
"max": 0.08005471900381962,
"count": 374
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.001419035327853635,
"min": 1.8255413092305162e-07,
"max": 0.08005471900381962,
"count": 374
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.001418234808370471,
"min": 2.47023378818767e-07,
"max": 0.12410455095989165,
"count": 374
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.001418234808370471,
"min": 2.47023378818767e-07,
"max": 0.12410455095989165,
"count": 374
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0008000000000000001,
"min": 0.0008000000000000001,
"max": 0.0008000000000000001,
"count": 374
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0008000000000000001,
"min": 0.0008000000000000001,
"max": 0.0008000000000000001,
"count": 374
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 374
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 374
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.009000000000000001,
"min": 0.009000000000000001,
"max": 0.009000000000000001,
"count": 374
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.009000000000000001,
"min": 0.009000000000000001,
"max": 0.009000000000000001,
"count": 374
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688801486",
"python_version": "3.9.6 (tags/v3.9.6:db3ff76, Jun 28 2021, 15:26:21) [MSC v.1929 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\DEVANSH\\Desktop\\ANPR\\FLOW YLO\\myenv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-dp-v25 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1688844978"
},
"total": 43492.2698454,
"count": 1,
"self": 0.5833446999968146,
"children": {
"run_training.setup": {
"total": 0.12334639999999997,
"count": 1,
"self": 0.12334639999999997
},
"TrainerController.start_learning": {
"total": 43491.5631543,
"count": 1,
"self": 11.520652901919675,
"children": {
"TrainerController._reset_env": {
"total": 9.01699820000043,
"count": 80,
"self": 9.01699820000043
},
"TrainerController.advance": {
"total": 43470.67259179807,
"count": 535317,
"self": 12.070175197572098,
"children": {
"env_step": {
"total": 10323.414654499755,
"count": 535317,
"self": 8007.558801104609,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2308.114078997449,
"count": 535317,
"self": 91.4996277973828,
"children": {
"TorchPolicy.evaluate": {
"total": 2216.614451200066,
"count": 1062488,
"self": 2216.614451200066
}
}
},
"workers": {
"total": 7.741774397696444,
"count": 535317,
"self": 0.0,
"children": {
"worker_root": {
"total": 43468.20035839868,
"count": 535317,
"is_parallel": true,
"self": 37006.63517729916,
"children": {
"steps_from_proto": {
"total": 0.14478219999247433,
"count": 160,
"is_parallel": true,
"self": 0.026452700027923992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.11832949996455033,
"count": 640,
"is_parallel": true,
"self": 0.11832949996455033
}
}
},
"UnityEnvironment.step": {
"total": 6461.420398899525,
"count": 535317,
"is_parallel": true,
"self": 347.783948401393,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 369.30587130041636,
"count": 535317,
"is_parallel": true,
"self": 369.30587130041636
},
"communicator.exchange": {
"total": 4773.880705000014,
"count": 535317,
"is_parallel": true,
"self": 4773.880705000014
},
"steps_from_proto": {
"total": 970.4498741977014,
"count": 1070634,
"is_parallel": true,
"self": 176.9166951975027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 793.5331790001987,
"count": 4282536,
"is_parallel": true,
"self": 793.5331790001987
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 33135.187762100744,
"count": 535317,
"self": 101.0589333003154,
"children": {
"process_trajectory": {
"total": 2480.757330400441,
"count": 535317,
"self": 2476.7327660004325,
"children": {
"RLTrainer._checkpoint": {
"total": 4.02456440000833,
"count": 16,
"self": 4.02456440000833
}
}
},
"_update_policy": {
"total": 30553.371498399985,
"count": 374,
"self": 1961.7362739003438,
"children": {
"TorchPOCAOptimizer.update": {
"total": 28591.63522449964,
"count": 18700,
"self": 28591.63522449964
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.999995770864189e-07,
"count": 1,
"self": 8.999995770864189e-07
},
"TrainerController._save_models": {
"total": 0.3529105000052368,
"count": 1,
"self": 0.006616100006795023,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3462943999984418,
"count": 1,
"self": 0.3462943999984418
}
}
}
}
}
}
}