Pyramids-v1 / run_logs /timers.json
gmojko's picture
v1 push
40820fe
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.47847840189933777,
"min": 0.47847840189933777,
"max": 1.503717303276062,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14446.2197265625,
"min": 14379.724609375,
"max": 45616.76953125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989982.0,
"min": 29957.0,
"max": 989982.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989982.0,
"min": 29957.0,
"max": 989982.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.47030115127563477,
"min": -0.10355046391487122,
"max": 0.5821890830993652,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 128.86251831054688,
"min": -24.95566177368164,
"max": 163.012939453125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.044841405004262924,
"min": -0.007838398218154907,
"max": 0.22660115361213684,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 12.286544799804688,
"min": -2.194751501083374,
"max": 54.38427734375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06726333507131563,
"min": 0.0647866495710332,
"max": 0.07574323198499237,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9416866909984188,
"min": 0.5302026238949467,
"max": 1.0445243834047668,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015774664233460845,
"min": 0.0002778407668338412,
"max": 0.015774664233460845,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2208452992684518,
"min": 0.0025005669015045707,
"max": 0.2208452992684518,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.570576047935712e-06,
"min": 7.570576047935712e-06,
"max": 0.00029523818730155715,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010598806467109997,
"min": 0.00010598806467109997,
"max": 0.0032545667151445,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252349285714284,
"min": 0.10252349285714284,
"max": 0.19841272857142855,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353288999999998,
"min": 1.3888890999999999,
"max": 2.4428464000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002620969364285714,
"min": 0.0002620969364285714,
"max": 0.009841431584285715,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00366935711,
"min": 0.00366935711,
"max": 0.10850706444999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008340899832546711,
"min": 0.008340899832546711,
"max": 0.36871060729026794,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1167725920677185,
"min": 0.1167725920677185,
"max": 2.5809743404388428,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 376.679012345679,
"min": 328.8315789473684,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30511.0,
"min": 16500.0,
"max": 32738.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5216899876482786,
"min": -0.999962551984936,
"max": 1.6501136629205002,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 121.73519901186228,
"min": -31.998801663517952,
"max": 156.7607979774475,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5216899876482786,
"min": -0.999962551984936,
"max": 1.6501136629205002,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 121.73519901186228,
"min": -31.998801663517952,
"max": 156.7607979774475,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03256438764874474,
"min": 0.030140007402836712,
"max": 7.050037117346244,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.6051510118995793,
"min": 2.5544534513610415,
"max": 119.85063099488616,
"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": "1674211405",
"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": "1674213298"
},
"total": 1893.0615450949995,
"count": 1,
"self": 0.44210948099953384,
"children": {
"run_training.setup": {
"total": 0.1048083650002809,
"count": 1,
"self": 0.1048083650002809
},
"TrainerController.start_learning": {
"total": 1892.5146272489997,
"count": 1,
"self": 1.079476537022856,
"children": {
"TrainerController._reset_env": {
"total": 5.904795376000038,
"count": 1,
"self": 5.904795376000038
},
"TrainerController.advance": {
"total": 1885.4460729709767,
"count": 63706,
"self": 1.1569529340263216,
"children": {
"env_step": {
"total": 1270.270090075006,
"count": 63706,
"self": 1174.386966176125,
"children": {
"SubprocessEnvManager._take_step": {
"total": 95.19792181092589,
"count": 63706,
"self": 3.958833522910936,
"children": {
"TorchPolicy.evaluate": {
"total": 91.23908828801495,
"count": 62561,
"self": 30.92962280299207,
"children": {
"TorchPolicy.sample_actions": {
"total": 60.30946548502288,
"count": 62561,
"self": 60.30946548502288
}
}
}
}
},
"workers": {
"total": 0.6852020879550764,
"count": 63706,
"self": 0.0,
"children": {
"worker_root": {
"total": 1889.4938977009215,
"count": 63706,
"is_parallel": true,
"self": 803.5562099529539,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016850179999892134,
"count": 1,
"is_parallel": true,
"self": 0.0006355479995363567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010494700004528568,
"count": 8,
"is_parallel": true,
"self": 0.0010494700004528568
}
}
},
"UnityEnvironment.step": {
"total": 0.04202519999989818,
"count": 1,
"is_parallel": true,
"self": 0.00047055799996087444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004455230000530719,
"count": 1,
"is_parallel": true,
"self": 0.0004455230000530719
},
"communicator.exchange": {
"total": 0.039644081000005826,
"count": 1,
"is_parallel": true,
"self": 0.039644081000005826
},
"steps_from_proto": {
"total": 0.0014650379998784047,
"count": 1,
"is_parallel": true,
"self": 0.000373733000287757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010913049995906476,
"count": 8,
"is_parallel": true,
"self": 0.0010913049995906476
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1085.9376877479676,
"count": 63705,
"is_parallel": true,
"self": 26.152350950108485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.498081100933632,
"count": 63705,
"is_parallel": true,
"self": 20.498081100933632
},
"communicator.exchange": {
"total": 947.071781520991,
"count": 63705,
"is_parallel": true,
"self": 947.071781520991
},
"steps_from_proto": {
"total": 92.21547417593456,
"count": 63705,
"is_parallel": true,
"self": 19.906551299705825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.30892287622873,
"count": 509640,
"is_parallel": true,
"self": 72.30892287622873
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 614.0190299619444,
"count": 63706,
"self": 2.0125257719164438,
"children": {
"process_trajectory": {
"total": 133.53603896002096,
"count": 63706,
"self": 133.35779897702105,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17823998299991217,
"count": 2,
"self": 0.17823998299991217
}
}
},
"_update_policy": {
"total": 478.470465230007,
"count": 442,
"self": 178.95210199401845,
"children": {
"TorchPPOOptimizer.update": {
"total": 299.51836323598855,
"count": 22827,
"self": 299.51836323598855
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.710001904750243e-07,
"count": 1,
"self": 9.710001904750243e-07
},
"TrainerController._save_models": {
"total": 0.08428139399984502,
"count": 1,
"self": 0.0015307920002669562,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08275060199957807,
"count": 1,
"self": 0.08275060199957807
}
}
}
}
}
}
}