ppo-PyramidsRND / run_logs /timers.json
hasarinduperera's picture
First Push
29ae210
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.552151083946228,
"min": 0.552151083946228,
"max": 1.4558590650558472,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16644.04296875,
"min": 16644.04296875,
"max": 44164.94140625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989955.0,
"min": 29952.0,
"max": 989955.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989955.0,
"min": 29952.0,
"max": 989955.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3636844754219055,
"min": -0.10641289502382278,
"max": 0.47799521684646606,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 95.64901733398438,
"min": -25.6455078125,
"max": 126.66873168945312,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.021166209131479263,
"min": 0.004009102936834097,
"max": 0.620877742767334,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.566712856292725,
"min": 1.010293960571289,
"max": 147.1480255126953,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06910800176013276,
"min": 0.06517872786821546,
"max": 0.07227048311368243,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9675120246418587,
"min": 0.5010011909571718,
"max": 1.0515442285007641,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01464001922387816,
"min": 0.00013603314699459673,
"max": 0.01464001922387816,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20496026913429424,
"min": 0.0016323977639351608,
"max": 0.2050744113900388,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.493861787792858e-06,
"min": 7.493861787792858e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010491406502910002,
"min": 0.00010491406502910002,
"max": 0.0029526769157744,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249792142857143,
"min": 0.10249792142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349709000000002,
"min": 1.3886848,
"max": 2.3173508,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025954235071428577,
"min": 0.00025954235071428577,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036335929100000004,
"min": 0.0036335929100000004,
"max": 0.09843413743999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013024529442191124,
"min": 0.013024529442191124,
"max": 0.5772071480751038,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18234340846538544,
"min": 0.18234340846538544,
"max": 4.040450096130371,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 452.2089552238806,
"min": 416.9855072463768,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30298.0,
"min": 15984.0,
"max": 32881.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4283492327181262,
"min": -1.0000000521540642,
"max": 1.4283492327181262,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 95.69939859211445,
"min": -31.99920167028904,
"max": 97.22339849919081,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4283492327181262,
"min": -1.0000000521540642,
"max": 1.4283492327181262,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 95.69939859211445,
"min": -31.99920167028904,
"max": 97.22339849919081,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06116954461626236,
"min": 0.060711062192727906,
"max": 12.781288802623749,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.098359489289578,
"min": 4.098359489289578,
"max": 204.50062084197998,
"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": "1678063570",
"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": "1678065883"
},
"total": 2313.0021632029993,
"count": 1,
"self": 0.47555276799994317,
"children": {
"run_training.setup": {
"total": 0.11520553399986966,
"count": 1,
"self": 0.11520553399986966
},
"TrainerController.start_learning": {
"total": 2312.4114049009995,
"count": 1,
"self": 1.6118450359126655,
"children": {
"TrainerController._reset_env": {
"total": 6.580679514999929,
"count": 1,
"self": 6.580679514999929
},
"TrainerController.advance": {
"total": 2304.118200006086,
"count": 63417,
"self": 1.8273183100554888,
"children": {
"env_step": {
"total": 1548.5871369999759,
"count": 63417,
"self": 1418.6558447889984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.88311030895738,
"count": 63417,
"self": 5.213398399991775,
"children": {
"TorchPolicy.evaluate": {
"total": 123.66971190896561,
"count": 62572,
"self": 41.40707005603144,
"children": {
"TorchPolicy.sample_actions": {
"total": 82.26264185293417,
"count": 62572,
"self": 82.26264185293417
}
}
}
}
},
"workers": {
"total": 1.0481819020201328,
"count": 63417,
"self": 0.0,
"children": {
"worker_root": {
"total": 2306.615420760061,
"count": 63417,
"is_parallel": true,
"self": 1018.8000522990815,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020695299999715644,
"count": 1,
"is_parallel": true,
"self": 0.0007867270003316662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012828029996398982,
"count": 8,
"is_parallel": true,
"self": 0.0012828029996398982
}
}
},
"UnityEnvironment.step": {
"total": 0.0879004089999853,
"count": 1,
"is_parallel": true,
"self": 0.0005269259997930931,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005034920000070997,
"count": 1,
"is_parallel": true,
"self": 0.0005034920000070997
},
"communicator.exchange": {
"total": 0.08531775100004779,
"count": 1,
"is_parallel": true,
"self": 0.08531775100004779
},
"steps_from_proto": {
"total": 0.0015522400001373171,
"count": 1,
"is_parallel": true,
"self": 0.000373878000118566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011783620000187511,
"count": 8,
"is_parallel": true,
"self": 0.0011783620000187511
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.8153684609797,
"count": 63416,
"is_parallel": true,
"self": 32.78771154008814,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.80047127104831,
"count": 63416,
"is_parallel": true,
"self": 25.80047127104831
},
"communicator.exchange": {
"total": 1127.431217531898,
"count": 63416,
"is_parallel": true,
"self": 1127.431217531898
},
"steps_from_proto": {
"total": 101.79596811794522,
"count": 63416,
"is_parallel": true,
"self": 25.17539693679305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.62057118115217,
"count": 507328,
"is_parallel": true,
"self": 76.62057118115217
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 753.7037446960549,
"count": 63417,
"self": 2.8748315291265953,
"children": {
"process_trajectory": {
"total": 171.56343195492218,
"count": 63417,
"self": 171.32180778192287,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24162417299930894,
"count": 2,
"self": 0.24162417299930894
}
}
},
"_update_policy": {
"total": 579.2654812120061,
"count": 436,
"self": 221.77690823700505,
"children": {
"TorchPPOOptimizer.update": {
"total": 357.48857297500103,
"count": 22836,
"self": 357.48857297500103
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4480001482297666e-06,
"count": 1,
"self": 1.4480001482297666e-06
},
"TrainerController._save_models": {
"total": 0.10067889600031776,
"count": 1,
"self": 0.00137914999959321,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09929974600072455,
"count": 1,
"self": 0.09929974600072455
}
}
}
}
}
}
}