poca-SoccerTwos / run_logs /timers.json
arrandi's picture
First Push
32cb631
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.3951915502548218,
"min": 1.2634586095809937,
"max": 3.2956900596618652,
"count": 5000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 28037.76953125,
"min": 10965.564453125,
"max": 116469.8515625,
"count": 5000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 66.2,
"min": 38.22047244094488,
"max": 999.0,
"count": 5000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19860.0,
"min": 13380.0,
"max": 30384.0,
"count": 5000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1628.9801477178667,
"min": 1186.4077939590866,
"max": 1710.7855163348008,
"count": 4967
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 244347.02215768,
"min": 2372.841061815623,
"max": 416996.4578146276,
"count": 4967
},
"SoccerTwos.Step.mean": {
"value": 49999944.0,
"min": 9208.0,
"max": 49999944.0,
"count": 5000
},
"SoccerTwos.Step.sum": {
"value": 49999944.0,
"min": 9208.0,
"max": 49999944.0,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.006404003128409386,
"min": -0.18173165619373322,
"max": 0.2155984342098236,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.9606004357337952,
"min": -30.894380569458008,
"max": 28.37074089050293,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.006341299507766962,
"min": -0.18270954489707947,
"max": 0.22243863344192505,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.9511949419975281,
"min": -31.060623168945312,
"max": 28.434301376342773,
"count": 5000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 5000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.07260000149408977,
"min": -0.6428571428571429,
"max": 0.5470181866125627,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -10.890000224113464,
"min": -67.69480049610138,
"max": 64.33120006322861,
"count": 5000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.07260000149408977,
"min": -0.6428571428571429,
"max": 0.5470181866125627,
"count": 5000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -10.890000224113464,
"min": -67.69480049610138,
"max": 64.33120006322861,
"count": 5000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.017803297971840947,
"min": 0.009804022525592397,
"max": 0.0272589957244539,
"count": 2424
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.017803297971840947,
"min": 0.009804022525592397,
"max": 0.0272589957244539,
"count": 2424
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09014217108488083,
"min": 5.6436319482600085e-06,
"max": 0.13003144264221192,
"count": 2424
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09014217108488083,
"min": 5.6436319482600085e-06,
"max": 0.13003144264221192,
"count": 2424
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09112853507200877,
"min": 5.387907996616074e-06,
"max": 0.13180518274505934,
"count": 2424
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09112853507200877,
"min": 5.387907996616074e-06,
"max": 0.13180518274505934,
"count": 2424
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 2424
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 2424
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 2424
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 2424
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 2424
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 2424
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679330450",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/aarriandiaga/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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",
"numpy_version": "1.21.2",
"end_time_seconds": "1679463673"
},
"total": 133223.42977892235,
"count": 1,
"self": 0.32382238283753395,
"children": {
"run_training.setup": {
"total": 0.019948072731494904,
"count": 1,
"self": 0.019948072731494904
},
"TrainerController.start_learning": {
"total": 133223.08600846678,
"count": 1,
"self": 73.28118709102273,
"children": {
"TrainerController._reset_env": {
"total": 15.53060756251216,
"count": 250,
"self": 15.53060756251216
},
"TrainerController.advance": {
"total": 133134.05893164128,
"count": 3468332,
"self": 73.12826198711991,
"children": {
"env_step": {
"total": 111102.08651187271,
"count": 3468332,
"self": 95785.77327330038,
"children": {
"SubprocessEnvManager._take_step": {
"total": 15273.147048886865,
"count": 3468333,
"self": 489.84687547013164,
"children": {
"TorchPolicy.evaluate": {
"total": 14783.300173416734,
"count": 6279312,
"self": 14783.300173416734
}
}
},
"workers": {
"total": 43.166189685463905,
"count": 3468332,
"self": 0.0,
"children": {
"worker_root": {
"total": 135271.72111195326,
"count": 3468332,
"is_parallel": true,
"self": 50016.85263640061,
"children": {
"run_training.setup": {
"total": 0.019948072731494904,
"count": 1,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004793088883161545,
"count": 2,
"is_parallel": true,
"self": 0.0010695457458496094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0037235431373119354,
"count": 8,
"is_parallel": true,
"self": 0.0037235431373119354
}
}
},
"UnityEnvironment.step": {
"total": 0.04481106624007225,
"count": 1,
"is_parallel": true,
"self": 0.0012932531535625458,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0008067935705184937,
"count": 1,
"is_parallel": true,
"self": 0.0008067935705184937
},
"communicator.exchange": {
"total": 0.038746923208236694,
"count": 1,
"is_parallel": true,
"self": 0.038746923208236694
},
"steps_from_proto": {
"total": 0.003964096307754517,
"count": 2,
"is_parallel": true,
"self": 0.0008054599165916443,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0031586363911628723,
"count": 8,
"is_parallel": true,
"self": 0.0031586363911628723
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 85253.62044411898,
"count": 3468330,
"is_parallel": true,
"self": 5210.795454546809,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3113.3619608581066,
"count": 3468330,
"is_parallel": true,
"self": 3113.3619608581066
},
"communicator.exchange": {
"total": 61663.338499210775,
"count": 3468330,
"is_parallel": true,
"self": 61663.338499210775
},
"steps_from_proto": {
"total": 15266.124529503286,
"count": 6936660,
"is_parallel": true,
"self": 2793.6784589216113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 12472.446070581675,
"count": 27746640,
"is_parallel": true,
"self": 12472.446070581675
}
}
}
}
},
"steps_from_proto": {
"total": 1.228083360940218,
"count": 498,
"is_parallel": true,
"self": 0.21993285417556763,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1.0081505067646503,
"count": 1992,
"is_parallel": true,
"self": 1.0081505067646503
}
}
},
"TrainerController.start_learning": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"TrainerController._reset_env": {
"total": 7.5863275825977325,
"count": 5,
"is_parallel": true,
"self": 7.5863275825977325
},
"TrainerController.advance": {
"total": 2281.6253745779395,
"count": 56449,
"is_parallel": true,
"self": 1.814806591719389,
"children": {
"env_step": {
"total": 1909.242174692452,
"count": 56449,
"is_parallel": true,
"self": 1554.839233968407,
"children": {
"SubprocessEnvManager._take_step": {
"total": 353.3750216551125,
"count": 56450,
"is_parallel": true,
"self": 12.837710570544004,
"children": {
"TorchPolicy.evaluate": {
"total": 340.5373110845685,
"count": 112116,
"is_parallel": true,
"self": 340.5373110845685
}
}
},
"workers": {
"total": 0.9727655313909054,
"count": 56449,
"is_parallel": true,
"self": 0.0,
"children": {
"worker_root": {
"total": 2285.767784692347,
"count": 56449,
"is_parallel": true,
"self": 950.0625123977661,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004793088883161545,
"count": 2,
"is_parallel": true,
"self": 0.0010695457458496094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0037235431373119354,
"count": 8,
"is_parallel": true,
"self": 0.0037235431373119354
}
}
},
"UnityEnvironment.step": {
"total": 0.04481106624007225,
"count": 1,
"is_parallel": true,
"self": 0.0012932531535625458,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0008067935705184937,
"count": 1,
"is_parallel": true,
"self": 0.0008067935705184937
},
"communicator.exchange": {
"total": 0.038746923208236694,
"count": 1,
"is_parallel": true,
"self": 0.038746923208236694
},
"steps_from_proto": {
"total": 0.003964096307754517,
"count": 2,
"is_parallel": true,
"self": 0.0008054599165916443,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0031586363911628723,
"count": 8,
"is_parallel": true,
"self": 0.0031586363911628723
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1335.6861735731363,
"count": 56448,
"is_parallel": true,
"self": 79.67445775866508,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 49.1990244500339,
"count": 56448,
"is_parallel": true,
"self": 49.1990244500339
},
"communicator.exchange": {
"total": 968.2461996413767,
"count": 56448,
"is_parallel": true,
"self": 968.2461996413767
},
"steps_from_proto": {
"total": 238.5664917230606,
"count": 112896,
"is_parallel": true,
"self": 43.785972483456135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 194.78051923960447,
"count": 451584,
"is_parallel": true,
"self": 194.78051923960447
}
}
}
}
},
"steps_from_proto": {
"total": 0.01909872144460678,
"count": 8,
"is_parallel": true,
"self": 0.0035157501697540283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.015582971274852753,
"count": 32,
"is_parallel": true,
"self": 0.015582971274852753
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.006959825754165649,
"count": 2,
"is_parallel": true,
"self": 0.0014488548040390015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005510970950126648,
"count": 8,
"is_parallel": true,
"self": 0.005510970950126648
}
}
},
"UnityEnvironment.step": {
"total": 0.048193711787462234,
"count": 1,
"is_parallel": true,
"self": 0.002052847295999527,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0011657513678073883,
"count": 1,
"is_parallel": true,
"self": 0.0011657513678073883
},
"communicator.exchange": {
"total": 0.03903596103191376,
"count": 1,
"is_parallel": true,
"self": 0.03903596103191376
},
"steps_from_proto": {
"total": 0.005939152091741562,
"count": 2,
"is_parallel": true,
"self": 0.000955536961555481,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004983615130186081,
"count": 8,
"is_parallel": true,
"self": 0.004983615130186081
}
}
}
}
}
}
},
"trainer_advance": {
"total": 370.56839329376817,
"count": 56449,
"is_parallel": true,
"self": 13.884199187159538,
"children": {
"process_trajectory": {
"total": 97.8659698329866,
"count": 56449,
"is_parallel": true,
"self": 97.61118080094457,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2547890320420265,
"count": 1,
"is_parallel": true,
"self": 0.2547890320420265
}
}
},
"_update_policy": {
"total": 258.81822427362204,
"count": 40,
"is_parallel": true,
"self": 177.95811439305544,
"children": {
"TorchPOCAOptimizer.update": {
"total": 80.8601098805666,
"count": 1200,
"is_parallel": true,
"self": 80.8601098805666
}
}
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 21958.844157781452,
"count": 3468332,
"self": 564.9205625094473,
"children": {
"process_trajectory": {
"total": 9854.32756850496,
"count": 3468332,
"self": 9830.445356227458,
"children": {
"RLTrainer._checkpoint": {
"total": 23.88221227750182,
"count": 100,
"self": 23.88221227750182
}
}
},
"_update_policy": {
"total": 11539.596026767045,
"count": 2424,
"self": 7461.798624768853,
"children": {
"TorchPOCAOptimizer.update": {
"total": 4077.797401998192,
"count": 72726,
"self": 4077.797401998192
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.087784767150879e-06,
"count": 1,
"self": 1.087784767150879e-06
},
"TrainerController._save_models": {
"total": 0.21528108417987823,
"count": 1,
"self": 0.002195604145526886,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21308548003435135,
"count": 1,
"self": 0.21308548003435135
}
}
}
}
}
}
}