ppo-Pyramids / run_logs /timers.json
thegadri's picture
First Push
589f800
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4018700122833252,
"min": 0.4018700122833252,
"max": 1.4350775480270386,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12036.810546875,
"min": 12036.810546875,
"max": 43534.51171875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989872.0,
"min": 29931.0,
"max": 989872.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989872.0,
"min": 29931.0,
"max": 989872.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4291709363460541,
"min": -0.1003846749663353,
"max": 0.4510374069213867,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 114.58863830566406,
"min": -24.192707061767578,
"max": 121.59211730957031,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.12871532142162323,
"min": -0.29952311515808105,
"max": 0.3012542724609375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 34.36698913574219,
"min": -77.27696228027344,
"max": 71.39726257324219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06853149934173385,
"min": 0.06248545042383915,
"max": 0.07411845370138088,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9594409907842739,
"min": 0.5785548281221162,
"max": 1.101118990792505,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01571607647034622,
"min": 0.000683094484836347,
"max": 0.035027163177510985,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22002507058484708,
"min": 0.009563322787708859,
"max": 0.4903802844851538,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.309147563650001e-06,
"min": 7.309147563650001e-06,
"max": 0.00029484236421921254,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010232806589110002,
"min": 0.00010232806589110002,
"max": 0.0035080658306448007,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243635,
"min": 0.10243635,
"max": 0.1982807875,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4341089,
"min": 1.4341089,
"max": 2.5693552,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002533913650000001,
"min": 0.0002533913650000001,
"max": 0.00982825067125,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035474791100000014,
"min": 0.0035474791100000014,
"max": 0.11695858448,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0389772430062294,
"min": 0.03439963608980179,
"max": 0.4212815761566162,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.5456814169883728,
"min": 0.48159489035606384,
"max": 3.3702526092529297,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 432.6119402985075,
"min": 408.1449275362319,
"max": 990.6451612903226,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28985.0,
"min": 16474.0,
"max": 33043.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4479581862688065,
"min": -0.9269355352847807,
"max": 1.5032849107703117,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 97.01319848001003,
"min": -28.7350015938282,
"max": 109.73979848623276,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4479581862688065,
"min": -0.9269355352847807,
"max": 1.5032849107703117,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 97.01319848001003,
"min": -28.7350015938282,
"max": 109.73979848623276,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.16827621915874613,
"min": 0.1605415181881087,
"max": 7.8126271016457505,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 11.274506683635991,
"min": 10.033745739725418,
"max": 132.81466072797775,
"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": "1699339447",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699341555"
},
"total": 2107.7923861,
"count": 1,
"self": 0.6259845929998846,
"children": {
"run_training.setup": {
"total": 0.041817002000016146,
"count": 1,
"self": 0.041817002000016146
},
"TrainerController.start_learning": {
"total": 2107.124584505,
"count": 1,
"self": 1.4352325329664382,
"children": {
"TrainerController._reset_env": {
"total": 3.509127883000019,
"count": 1,
"self": 3.509127883000019
},
"TrainerController.advance": {
"total": 2102.1061824810336,
"count": 63639,
"self": 1.4983415221372525,
"children": {
"env_step": {
"total": 1479.6431157289064,
"count": 63639,
"self": 1346.6363980539609,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.12146416595942,
"count": 63639,
"self": 4.500532179996526,
"children": {
"TorchPolicy.evaluate": {
"total": 127.6209319859629,
"count": 62565,
"self": 127.6209319859629
}
}
},
"workers": {
"total": 0.8852535089861249,
"count": 63639,
"self": 0.0,
"children": {
"worker_root": {
"total": 2102.48711151498,
"count": 63639,
"is_parallel": true,
"self": 870.0995381949504,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001848547999998118,
"count": 1,
"is_parallel": true,
"self": 0.0005389489997469354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013095990002511826,
"count": 8,
"is_parallel": true,
"self": 0.0013095990002511826
}
}
},
"UnityEnvironment.step": {
"total": 0.04791475100000753,
"count": 1,
"is_parallel": true,
"self": 0.0006117840000570141,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043979099996249715,
"count": 1,
"is_parallel": true,
"self": 0.00043979099996249715
},
"communicator.exchange": {
"total": 0.045269417999861616,
"count": 1,
"is_parallel": true,
"self": 0.045269417999861616
},
"steps_from_proto": {
"total": 0.0015937580001263996,
"count": 1,
"is_parallel": true,
"self": 0.0003447839999353164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012489740001910832,
"count": 8,
"is_parallel": true,
"self": 0.0012489740001910832
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1232.3875733200296,
"count": 63638,
"is_parallel": true,
"self": 34.23408714904576,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.513298410933203,
"count": 63638,
"is_parallel": true,
"self": 23.513298410933203
},
"communicator.exchange": {
"total": 1078.6848905520242,
"count": 63638,
"is_parallel": true,
"self": 1078.6848905520242
},
"steps_from_proto": {
"total": 95.95529720802642,
"count": 63638,
"is_parallel": true,
"self": 19.41722347287987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.53807373514655,
"count": 509104,
"is_parallel": true,
"self": 76.53807373514655
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 620.9647252299901,
"count": 63639,
"self": 2.794487064936675,
"children": {
"process_trajectory": {
"total": 116.70510642005706,
"count": 63639,
"self": 116.54576332905776,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15934309099930033,
"count": 2,
"self": 0.15934309099930033
}
}
},
"_update_policy": {
"total": 501.46513174499637,
"count": 456,
"self": 300.4191783069475,
"children": {
"TorchPPOOptimizer.update": {
"total": 201.04595343804885,
"count": 22818,
"self": 201.04595343804885
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2549999155453406e-06,
"count": 1,
"self": 1.2549999155453406e-06
},
"TrainerController._save_models": {
"total": 0.074040352999873,
"count": 1,
"self": 0.001364979999834759,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07267537300003823,
"count": 1,
"self": 0.07267537300003823
}
}
}
}
}
}
}