ppo-Pyramids / run_logs /timers.json
Akriel's picture
Upload Model
fb0e90b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3497735261917114,
"min": 0.3497735261917114,
"max": 1.4445520639419556,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10493.2060546875,
"min": 10493.2060546875,
"max": 43821.9296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989930.0,
"min": 29928.0,
"max": 989930.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989930.0,
"min": 29928.0,
"max": 989930.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4746772348880768,
"min": -0.14388424158096313,
"max": 0.5719482898712158,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 131.485595703125,
"min": -34.10056686401367,
"max": 161.07473754882812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010207213461399078,
"min": 0.010207213461399078,
"max": 0.6037054657936096,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.8273980617523193,
"min": 2.725677967071533,
"max": 143.0782012939453,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06896265623286393,
"min": 0.06490878107229865,
"max": 0.07765901404163802,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9654771872600951,
"min": 0.5436130982914662,
"max": 1.1096215255115656,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017271248600739173,
"min": 0.0008498618186019502,
"max": 0.01738655109725911,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24179748041034843,
"min": 0.009348480004621452,
"max": 0.24179748041034843,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.589904612921428e-06,
"min": 7.589904612921428e-06,
"max": 0.00029523394444582856,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001062586645809,
"min": 0.0001062586645809,
"max": 0.0033758281747239996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252993571428572,
"min": 0.10252993571428572,
"max": 0.19841131428571426,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354191,
"min": 1.3888791999999999,
"max": 2.4435932,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026274057785714285,
"min": 0.00026274057785714285,
"max": 0.009841290297142856,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00367836809,
"min": 0.00367836809,
"max": 0.11254507240000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01584993302822113,
"min": 0.0152517631649971,
"max": 0.8268431425094604,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.22189906239509583,
"min": 0.2135246843099594,
"max": 5.787901878356934,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 352.9655172413793,
"min": 342.1847826086956,
"max": 993.4375,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30708.0,
"min": 16599.0,
"max": 32806.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.548763612623919,
"min": -0.9318688006605953,
"max": 1.6153815881102935,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 136.29119791090488,
"min": -29.81980162113905,
"max": 147.3751990571618,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.548763612623919,
"min": -0.9318688006605953,
"max": 1.6153815881102935,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 136.29119791090488,
"min": -29.81980162113905,
"max": 147.3751990571618,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.058866125844360795,
"min": 0.058866125844360795,
"max": 17.007375899483176,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.18021907430375,
"min": 4.2984048268408515,
"max": 289.125390291214,
"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": "1677077693",
"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": "1677079978"
},
"total": 2285.4119829049996,
"count": 1,
"self": 0.48610340299910604,
"children": {
"run_training.setup": {
"total": 0.10840098499988926,
"count": 1,
"self": 0.10840098499988926
},
"TrainerController.start_learning": {
"total": 2284.8174785170004,
"count": 1,
"self": 1.3346615880000172,
"children": {
"TrainerController._reset_env": {
"total": 7.4696353959998305,
"count": 1,
"self": 7.4696353959998305
},
"TrainerController.advance": {
"total": 2275.9244520500006,
"count": 63836,
"self": 1.454064656943956,
"children": {
"env_step": {
"total": 1531.3688211179683,
"count": 63836,
"self": 1414.6531560408353,
"children": {
"SubprocessEnvManager._take_step": {
"total": 115.84543569500033,
"count": 63836,
"self": 4.7331735050970565,
"children": {
"TorchPolicy.evaluate": {
"total": 111.11226218990328,
"count": 62560,
"self": 37.1243314579076,
"children": {
"TorchPolicy.sample_actions": {
"total": 73.98793073199568,
"count": 62560,
"self": 73.98793073199568
}
}
}
}
},
"workers": {
"total": 0.8702293821327203,
"count": 63836,
"self": 0.0,
"children": {
"worker_root": {
"total": 2279.7883629990515,
"count": 63836,
"is_parallel": true,
"self": 981.270275633969,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018662290001429938,
"count": 1,
"is_parallel": true,
"self": 0.0007131270001536905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011531019999893033,
"count": 8,
"is_parallel": true,
"self": 0.0011531019999893033
}
}
},
"UnityEnvironment.step": {
"total": 0.047237965000022086,
"count": 1,
"is_parallel": true,
"self": 0.0005570079999870359,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000506052999980966,
"count": 1,
"is_parallel": true,
"self": 0.000506052999980966
},
"communicator.exchange": {
"total": 0.04447088100005203,
"count": 1,
"is_parallel": true,
"self": 0.04447088100005203
},
"steps_from_proto": {
"total": 0.0017040230000020529,
"count": 1,
"is_parallel": true,
"self": 0.00042193599983875174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012820870001633011,
"count": 8,
"is_parallel": true,
"self": 0.0012820870001633011
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.5180873650825,
"count": 63835,
"is_parallel": true,
"self": 31.51418464501785,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.509126260049015,
"count": 63835,
"is_parallel": true,
"self": 22.509126260049015
},
"communicator.exchange": {
"total": 1150.8409563700086,
"count": 63835,
"is_parallel": true,
"self": 1150.8409563700086
},
"steps_from_proto": {
"total": 93.653820090007,
"count": 63835,
"is_parallel": true,
"self": 22.146441893168912,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.50737819683809,
"count": 510680,
"is_parallel": true,
"self": 71.50737819683809
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 743.1015662750881,
"count": 63836,
"self": 2.6131323361778414,
"children": {
"process_trajectory": {
"total": 162.74458723391172,
"count": 63836,
"self": 162.5562134709112,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1883737630005271,
"count": 2,
"self": 0.1883737630005271
}
}
},
"_update_policy": {
"total": 577.7438467049985,
"count": 449,
"self": 219.50917837692464,
"children": {
"TorchPPOOptimizer.update": {
"total": 358.2346683280739,
"count": 22788,
"self": 358.2346683280739
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.08872862099997292,
"count": 1,
"self": 0.0013979629993627896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08733065800061013,
"count": 1,
"self": 0.08733065800061013
}
}
}
}
}
}
}