ppo-Pyramids / run_logs /timers.json
jrnold's picture
Initial commit
0bf65da
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.662866473197937,
"min": 0.6308479309082031,
"max": 1.4640930891036987,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 19854.17578125,
"min": 19127.30859375,
"max": 44414.7265625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989987.0,
"min": 29952.0,
"max": 989987.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989987.0,
"min": 29952.0,
"max": 989987.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.08998654037714005,
"min": -0.1181393712759018,
"max": 0.0922677293419838,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 22.136688232421875,
"min": -27.99903106689453,
"max": 22.790128707885742,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.015939606353640556,
"min": 0.007343046832829714,
"max": 0.25488677620887756,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.921143054962158,
"min": 1.806389570236206,
"max": 60.805145263671875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.069589979658143,
"min": 0.06467414846688996,
"max": 0.07427116272477921,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.974259715214002,
"min": 0.5005502260121819,
"max": 1.0740353117837322,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005884176913770018,
"min": 0.00034734076966702626,
"max": 0.005884176913770018,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08237847679278025,
"min": 0.004862770775338368,
"max": 0.08237847679278025,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.293783283057141e-06,
"min": 7.293783283057141e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010211296596279997,
"min": 0.00010211296596279997,
"max": 0.0032556579147808,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243122857142857,
"min": 0.10243122857142857,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340372,
"min": 1.3886848,
"max": 2.4852192,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002528797342857142,
"min": 0.0002528797342857142,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035403162799999993,
"min": 0.0035403162799999993,
"max": 0.10855339808,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010356682352721691,
"min": 0.010356682352721691,
"max": 0.3740040361881256,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14499355852603912,
"min": 0.14499355852603912,
"max": 2.618028163909912,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 773.7692307692307,
"min": 757.421052631579,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30177.0,
"min": 15984.0,
"max": 32335.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.1792157502158692,
"min": -1.0000000521540642,
"max": 0.5055473270384889,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 6.81019850820303,
"min": -30.767001643776894,
"max": 19.210798427462578,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.1792157502158692,
"min": -1.0000000521540642,
"max": 0.5055473270384889,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 6.81019850820303,
"min": -30.767001643776894,
"max": 19.210798427462578,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08352607121923938,
"min": 0.08101107078714688,
"max": 7.726586662232876,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.1739907063310966,
"min": 3.0784206899115816,
"max": 123.62538659572601,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674163185",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674165033"
},
"total": 1847.690558823,
"count": 1,
"self": 0.4421605930001533,
"children": {
"run_training.setup": {
"total": 0.10403113899997152,
"count": 1,
"self": 0.10403113899997152
},
"TrainerController.start_learning": {
"total": 1847.1443670909998,
"count": 1,
"self": 1.1540014119354964,
"children": {
"TrainerController._reset_env": {
"total": 9.804726406999976,
"count": 1,
"self": 9.804726406999976
},
"TrainerController.advance": {
"total": 1836.102238351064,
"count": 63289,
"self": 1.2213976940511202,
"children": {
"env_step": {
"total": 1185.4669462320226,
"count": 63289,
"self": 1086.4099459909737,
"children": {
"SubprocessEnvManager._take_step": {
"total": 98.33799725499796,
"count": 63289,
"self": 4.209547167927212,
"children": {
"TorchPolicy.evaluate": {
"total": 94.12845008707075,
"count": 62581,
"self": 32.22867376409613,
"children": {
"TorchPolicy.sample_actions": {
"total": 61.89977632297462,
"count": 62581,
"self": 61.89977632297462
}
}
}
}
},
"workers": {
"total": 0.7190029860508957,
"count": 63289,
"self": 0.0,
"children": {
"worker_root": {
"total": 1843.699930361055,
"count": 63289,
"is_parallel": true,
"self": 849.156519594069,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007131883999932143,
"count": 1,
"is_parallel": true,
"self": 0.004048584999964078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003083298999968065,
"count": 8,
"is_parallel": true,
"self": 0.003083298999968065
}
}
},
"UnityEnvironment.step": {
"total": 0.07658844999991743,
"count": 1,
"is_parallel": true,
"self": 0.0005168799999637486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042476900000565365,
"count": 1,
"is_parallel": true,
"self": 0.00042476900000565365
},
"communicator.exchange": {
"total": 0.07389368099995863,
"count": 1,
"is_parallel": true,
"self": 0.07389368099995863
},
"steps_from_proto": {
"total": 0.0017531199999893943,
"count": 1,
"is_parallel": true,
"self": 0.0004675400000451191,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012855799999442752,
"count": 8,
"is_parallel": true,
"self": 0.0012855799999442752
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 994.5434107669861,
"count": 63288,
"is_parallel": true,
"self": 26.601608385975055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.303312162015686,
"count": 63288,
"is_parallel": true,
"self": 21.303312162015686
},
"communicator.exchange": {
"total": 852.2756267709768,
"count": 63288,
"is_parallel": true,
"self": 852.2756267709768
},
"steps_from_proto": {
"total": 94.36286344801852,
"count": 63288,
"is_parallel": true,
"self": 20.36618073598538,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.99668271203313,
"count": 506304,
"is_parallel": true,
"self": 73.99668271203313
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 649.4138944249903,
"count": 63289,
"self": 2.106544071983535,
"children": {
"process_trajectory": {
"total": 139.68450533500788,
"count": 63289,
"self": 139.5018013810078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18270395400008965,
"count": 2,
"self": 0.18270395400008965
}
}
},
"_update_policy": {
"total": 507.6228450179989,
"count": 446,
"self": 191.18666937197077,
"children": {
"TorchPPOOptimizer.update": {
"total": 316.4361756460281,
"count": 22812,
"self": 316.4361756460281
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1860001905006357e-06,
"count": 1,
"self": 1.1860001905006357e-06
},
"TrainerController._save_models": {
"total": 0.08339973500005726,
"count": 1,
"self": 0.0014513300002363394,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08194840499982092,
"count": 1,
"self": 0.08194840499982092
}
}
}
}
}
}
}