jrreda's picture
First Push
9491725
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2815423011779785,
"min": 0.2815423011779785,
"max": 1.4550840854644775,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8450.7734375,
"min": 8450.7734375,
"max": 44141.4296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989881.0,
"min": 29952.0,
"max": 989881.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989881.0,
"min": 29952.0,
"max": 989881.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6494620442390442,
"min": -0.11230196803808212,
"max": 0.7135135531425476,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 188.343994140625,
"min": -27.17707633972168,
"max": 209.77297973632812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.005495206918567419,
"min": -0.013067376799881458,
"max": 0.26918575167655945,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.5936100482940674,
"min": -3.5673937797546387,
"max": 64.87376403808594,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0689608024743696,
"min": 0.0662408108620905,
"max": 0.07453571287139009,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9654512346411744,
"min": 0.4780832915501629,
"max": 1.1180356930708513,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017662846058859333,
"min": 0.0021753893195138752,
"max": 0.017662846058859333,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24727984482403065,
"min": 0.017403114556111002,
"max": 0.24727984482403065,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.492511788242864e-06,
"min": 7.492511788242864e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010489516503540009,
"min": 0.00010489516503540009,
"max": 0.0035056934314356,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249747142857144,
"min": 0.10249747142857144,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349646,
"min": 1.3886848,
"max": 2.6625814,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025949739571428596,
"min": 0.00025949739571428596,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036329635400000034,
"min": 0.0036329635400000034,
"max": 0.11687958356,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010759315453469753,
"min": 0.010759315453469753,
"max": 0.37422314286231995,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1506304144859314,
"min": 0.1506304144859314,
"max": 2.6195619106292725,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 272.7264957264957,
"min": 249.48739495798318,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31909.0,
"min": 15984.0,
"max": 32625.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6075845954255161,
"min": -1.0000000521540642,
"max": 1.7168840236899232,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 188.08739766478539,
"min": -30.421001628041267,
"max": 204.30919881910086,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6075845954255161,
"min": -1.0000000521540642,
"max": 1.7168840236899232,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 188.08739766478539,
"min": -30.421001628041267,
"max": 204.30919881910086,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.029987596093306843,
"min": 0.029987596093306843,
"max": 7.3839668976143,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.5085487429169007,
"min": 3.3023280949273612,
"max": 118.1434703618288,
"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": "1682357269",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1682359574"
},
"total": 2305.29318363,
"count": 1,
"self": 0.4871779729996888,
"children": {
"run_training.setup": {
"total": 0.11586501199997201,
"count": 1,
"self": 0.11586501199997201
},
"TrainerController.start_learning": {
"total": 2304.690140645,
"count": 1,
"self": 1.4023367619911369,
"children": {
"TrainerController._reset_env": {
"total": 4.12570871500003,
"count": 1,
"self": 4.12570871500003
},
"TrainerController.advance": {
"total": 2299.057750876009,
"count": 64387,
"self": 1.5263166099516638,
"children": {
"env_step": {
"total": 1671.3568434010074,
"count": 64387,
"self": 1564.1425922638955,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.33981198205106,
"count": 64387,
"self": 4.857207012073445,
"children": {
"TorchPolicy.evaluate": {
"total": 101.48260496997761,
"count": 62563,
"self": 101.48260496997761
}
}
},
"workers": {
"total": 0.874439155060827,
"count": 64387,
"self": 0.0,
"children": {
"worker_root": {
"total": 2299.375623469037,
"count": 64387,
"is_parallel": true,
"self": 848.8824882500062,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005320654000001923,
"count": 1,
"is_parallel": true,
"self": 0.004069599000104063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012510549998978604,
"count": 8,
"is_parallel": true,
"self": 0.0012510549998978604
}
}
},
"UnityEnvironment.step": {
"total": 0.04762625600000092,
"count": 1,
"is_parallel": true,
"self": 0.000646351000057166,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004949579999902198,
"count": 1,
"is_parallel": true,
"self": 0.0004949579999902198
},
"communicator.exchange": {
"total": 0.04457419699997445,
"count": 1,
"is_parallel": true,
"self": 0.04457419699997445
},
"steps_from_proto": {
"total": 0.001910749999979089,
"count": 1,
"is_parallel": true,
"self": 0.00041699799999150855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014937519999875803,
"count": 8,
"is_parallel": true,
"self": 0.0014937519999875803
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1450.4931352190306,
"count": 64386,
"is_parallel": true,
"self": 33.80792670599567,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.449786765991178,
"count": 64386,
"is_parallel": true,
"self": 23.449786765991178
},
"communicator.exchange": {
"total": 1297.828497051004,
"count": 64386,
"is_parallel": true,
"self": 1297.828497051004
},
"steps_from_proto": {
"total": 95.40692469603977,
"count": 64386,
"is_parallel": true,
"self": 20.46580753797781,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.94111715806196,
"count": 515088,
"is_parallel": true,
"self": 74.94111715806196
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 626.1745908650498,
"count": 64387,
"self": 2.6917020370925684,
"children": {
"process_trajectory": {
"total": 107.81851463695932,
"count": 64387,
"self": 107.59544917995925,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22306545700007518,
"count": 2,
"self": 0.22306545700007518
}
}
},
"_update_policy": {
"total": 515.6643741909979,
"count": 455,
"self": 332.18410507097195,
"children": {
"TorchPPOOptimizer.update": {
"total": 183.48026912002598,
"count": 22836,
"self": 183.48026912002598
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.930001058615744e-07,
"count": 1,
"self": 8.930001058615744e-07
},
"TrainerController._save_models": {
"total": 0.1043433989998448,
"count": 1,
"self": 0.0016228260001298622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10272057299971493,
"count": 1,
"self": 0.10272057299971493
}
}
}
}
}
}
}