ppo-Pyramids / run_logs /timers.json
Aitor's picture
First try
ad476b7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2997375428676605,
"min": 0.2769142985343933,
"max": 1.4413154125213623,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8992.1259765625,
"min": 8311.859375,
"max": 43723.74609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989920.0,
"min": 29952.0,
"max": 989920.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989920.0,
"min": 29952.0,
"max": 989920.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4801728129386902,
"min": -0.1075386255979538,
"max": 0.48062360286712646,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 132.52769470214844,
"min": -25.91680908203125,
"max": 132.52769470214844,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.002971525536850095,
"min": -0.002971525536850095,
"max": 0.41714349389076233,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.820141077041626,
"min": -0.820141077041626,
"max": 98.86300659179688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06574068797081487,
"min": 0.06574068797081487,
"max": 0.07203497486563161,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9203696315914082,
"min": 0.5023464154336339,
"max": 1.0414370572155651,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01598917196644747,
"min": 0.0008134882148754913,
"max": 0.015995215729470998,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2238484075302646,
"min": 0.009761858578505896,
"max": 0.2258803494820741,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.599226038385714e-06,
"min": 7.599226038385714e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001063891645374,
"min": 0.0001063891645374,
"max": 0.0033827021724327005,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253304285714285,
"min": 0.10253304285714285,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354626,
"min": 1.3886848,
"max": 2.5275673,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026305098142857147,
"min": 0.00026305098142857147,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036827137400000007,
"min": 0.0036827137400000007,
"max": 0.11278397326999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01184776984155178,
"min": 0.011172222904860973,
"max": 0.5015940070152283,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16586877405643463,
"min": 0.15641112625598907,
"max": 3.511157989501953,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 373.39285714285717,
"min": 373.39285714285717,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31365.0,
"min": 15984.0,
"max": 32982.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5551618823692912,
"min": -1.0000000521540642,
"max": 1.5551618823692912,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 130.63359811902046,
"min": -30.676601640880108,
"max": 130.63359811902046,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5551618823692912,
"min": -1.0000000521540642,
"max": 1.5551618823692912,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 130.63359811902046,
"min": -30.676601640880108,
"max": 130.63359811902046,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04598638377397687,
"min": 0.04519698418742927,
"max": 9.99593931157142,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.862856237014057,
"min": 3.344576829869766,
"max": 159.9350289851427,
"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": "1677711661",
"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=Pyramids1 --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": "1677713913"
},
"total": 2251.551721145,
"count": 1,
"self": 0.4768355009996412,
"children": {
"run_training.setup": {
"total": 0.1263449830000809,
"count": 1,
"self": 0.1263449830000809
},
"TrainerController.start_learning": {
"total": 2250.948540661,
"count": 1,
"self": 1.332538972007569,
"children": {
"TrainerController._reset_env": {
"total": 6.071195744999841,
"count": 1,
"self": 6.071195744999841
},
"TrainerController.advance": {
"total": 2243.4513331019925,
"count": 63720,
"self": 1.4924420860620558,
"children": {
"env_step": {
"total": 1498.9373597340002,
"count": 63720,
"self": 1381.4999846609512,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.59669930300402,
"count": 63720,
"self": 4.868130420065654,
"children": {
"TorchPolicy.evaluate": {
"total": 111.72856888293836,
"count": 62555,
"self": 37.91285198796868,
"children": {
"TorchPolicy.sample_actions": {
"total": 73.81571689496968,
"count": 62555,
"self": 73.81571689496968
}
}
}
}
},
"workers": {
"total": 0.8406757700449816,
"count": 63720,
"self": 0.0,
"children": {
"worker_root": {
"total": 2245.9474925740105,
"count": 63720,
"is_parallel": true,
"self": 983.4908595560887,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001967926999896008,
"count": 1,
"is_parallel": true,
"self": 0.0007443379997766897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012235890001193184,
"count": 8,
"is_parallel": true,
"self": 0.0012235890001193184
}
}
},
"UnityEnvironment.step": {
"total": 0.052328064999983326,
"count": 1,
"is_parallel": true,
"self": 0.0005605529997865233,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005305550000684889,
"count": 1,
"is_parallel": true,
"self": 0.0005305550000684889
},
"communicator.exchange": {
"total": 0.049212941999940085,
"count": 1,
"is_parallel": true,
"self": 0.049212941999940085
},
"steps_from_proto": {
"total": 0.0020240150001882284,
"count": 1,
"is_parallel": true,
"self": 0.0004576040005304094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001566410999657819,
"count": 8,
"is_parallel": true,
"self": 0.001566410999657819
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1262.4566330179218,
"count": 63719,
"is_parallel": true,
"self": 31.72713848082958,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.556772993083996,
"count": 63719,
"is_parallel": true,
"self": 24.556772993083996
},
"communicator.exchange": {
"total": 1109.9606059290008,
"count": 63719,
"is_parallel": true,
"self": 1109.9606059290008
},
"steps_from_proto": {
"total": 96.2121156150074,
"count": 63719,
"is_parallel": true,
"self": 23.247973966747622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.96414164825978,
"count": 509752,
"is_parallel": true,
"self": 72.96414164825978
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 743.0215312819303,
"count": 63720,
"self": 2.526514928908,
"children": {
"process_trajectory": {
"total": 169.28641739501745,
"count": 63720,
"self": 169.0971259130174,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1892914820000442,
"count": 2,
"self": 0.1892914820000442
}
}
},
"_update_policy": {
"total": 571.2085989580048,
"count": 447,
"self": 218.02671510499044,
"children": {
"TorchPPOOptimizer.update": {
"total": 353.18188385301437,
"count": 22857,
"self": 353.18188385301437
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.710001904750243e-07,
"count": 1,
"self": 9.710001904750243e-07
},
"TrainerController._save_models": {
"total": 0.09347187100001975,
"count": 1,
"self": 0.0013875159997951414,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0920843550002246,
"count": 1,
"self": 0.0920843550002246
}
}
}
}
}
}
}