ppo-pyramids / run_logs /timers.json
haanjack's picture
First Push
8633fe8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.45376408100128174,
"min": 0.45376408100128174,
"max": 1.4036492109298706,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13634.703125,
"min": 13634.703125,
"max": 42581.1015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989921.0,
"min": 29952.0,
"max": 989921.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989921.0,
"min": 29952.0,
"max": 989921.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5295442342758179,
"min": -0.1182449609041214,
"max": 0.5941707491874695,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 142.44740295410156,
"min": -28.3787899017334,
"max": 164.58529663085938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.022743867710232735,
"min": -0.044312041252851486,
"max": 0.45654407143592834,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -6.118100166320801,
"min": -11.919939041137695,
"max": 108.20094299316406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06775370480248795,
"min": 0.06601439321206676,
"max": 0.07429145222969344,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9485518672348312,
"min": 0.5056378596934661,
"max": 1.040080331215708,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014007220935170718,
"min": 0.0011068042062915156,
"max": 0.014007220935170718,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19610109309239004,
"min": 0.009176805346460346,
"max": 0.19610109309239004,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.735275993035715e-06,
"min": 7.735275993035715e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010829386390250002,
"min": 0.00010829386390250002,
"max": 0.0035083490305504008,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257839285714286,
"min": 0.10257839285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4360975,
"min": 1.3691136000000002,
"max": 2.572439900000001,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002675814464285715,
"min": 0.0002675814464285715,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003746140250000001,
"min": 0.003746140250000001,
"max": 0.11696801504000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011737602762877941,
"min": 0.011588207446038723,
"max": 0.4439639449119568,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16432644426822662,
"min": 0.16223490238189697,
"max": 3.1077475547790527,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 366.0238095238095,
"min": 326.23333333333335,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30746.0,
"min": 15984.0,
"max": 32969.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4910618796767223,
"min": -1.0000000521540642,
"max": 1.6282527319022588,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 125.24919789284468,
"min": -32.000001668930054,
"max": 148.17099860310555,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4910618796767223,
"min": -1.0000000521540642,
"max": 1.6282527319022588,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 125.24919789284468,
"min": -32.000001668930054,
"max": 148.17099860310555,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0439306872871211,
"min": 0.04077954309452632,
"max": 8.555007913149893,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.6901777321181726,
"min": 3.608585894864518,
"max": 136.8801266103983,
"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": "1677792127",
"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": "1.22.4",
"end_time_seconds": "1677794403"
},
"total": 2275.167158759,
"count": 1,
"self": 0.48838378399977955,
"children": {
"run_training.setup": {
"total": 0.1070991450000065,
"count": 1,
"self": 0.1070991450000065
},
"TrainerController.start_learning": {
"total": 2274.57167583,
"count": 1,
"self": 1.468538395060932,
"children": {
"TrainerController._reset_env": {
"total": 6.070337718000019,
"count": 1,
"self": 6.070337718000019
},
"TrainerController.advance": {
"total": 2266.94677637294,
"count": 63830,
"self": 1.5372096270157272,
"children": {
"env_step": {
"total": 1535.0118303810295,
"count": 63830,
"self": 1415.1788922760397,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.90281205397514,
"count": 63830,
"self": 5.021596235904553,
"children": {
"TorchPolicy.evaluate": {
"total": 113.88121581807059,
"count": 62553,
"self": 38.72681349207642,
"children": {
"TorchPolicy.sample_actions": {
"total": 75.15440232599417,
"count": 62553,
"self": 75.15440232599417
}
}
}
}
},
"workers": {
"total": 0.9301260510145539,
"count": 63830,
"self": 0.0,
"children": {
"worker_root": {
"total": 2269.125695109993,
"count": 63830,
"is_parallel": true,
"self": 978.5161959869997,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018669749999844498,
"count": 1,
"is_parallel": true,
"self": 0.000712176999741132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011547980002433178,
"count": 8,
"is_parallel": true,
"self": 0.0011547980002433178
}
}
},
"UnityEnvironment.step": {
"total": 0.06381208299990249,
"count": 1,
"is_parallel": true,
"self": 0.0005578459999924235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005180869999321658,
"count": 1,
"is_parallel": true,
"self": 0.0005180869999321658
},
"communicator.exchange": {
"total": 0.06075170999997681,
"count": 1,
"is_parallel": true,
"self": 0.06075170999997681
},
"steps_from_proto": {
"total": 0.0019844400000010864,
"count": 1,
"is_parallel": true,
"self": 0.0007372329999952854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001247207000005801,
"count": 8,
"is_parallel": true,
"self": 0.001247207000005801
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1290.6094991229934,
"count": 63829,
"is_parallel": true,
"self": 31.753506332970574,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.875371616005623,
"count": 63829,
"is_parallel": true,
"self": 24.875371616005623
},
"communicator.exchange": {
"total": 1137.644962234005,
"count": 63829,
"is_parallel": true,
"self": 1137.644962234005
},
"steps_from_proto": {
"total": 96.33565894001197,
"count": 63829,
"is_parallel": true,
"self": 23.801582406763714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.53407653324825,
"count": 510632,
"is_parallel": true,
"self": 72.53407653324825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 730.3977363648945,
"count": 63830,
"self": 2.8160904748375515,
"children": {
"process_trajectory": {
"total": 170.04280100305107,
"count": 63830,
"self": 169.85939835605143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18340264699963882,
"count": 2,
"self": 0.18340264699963882
}
}
},
"_update_policy": {
"total": 557.5388448870059,
"count": 446,
"self": 216.67180056597942,
"children": {
"TorchPPOOptimizer.update": {
"total": 340.86704432102647,
"count": 22761,
"self": 340.86704432102647
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.879997039912269e-07,
"count": 1,
"self": 8.879997039912269e-07
},
"TrainerController._save_models": {
"total": 0.08602245599968228,
"count": 1,
"self": 0.0014179309996507072,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08460452500003157,
"count": 1,
"self": 0.08460452500003157
}
}
}
}
}
}
}