jinghuanHuggingface's picture
First Pyramids
64c8762 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.44687166810035706,
"min": 0.44687166810035706,
"max": 1.4906100034713745,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13434.75,
"min": 13298.4658203125,
"max": 45219.14453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989971.0,
"min": 29952.0,
"max": 989971.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989971.0,
"min": 29952.0,
"max": 989971.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.35923877358436584,
"min": -0.10308241099119186,
"max": 0.37790781259536743,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 95.91675567626953,
"min": -24.84286117553711,
"max": 98.63394165039062,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.01777919940650463,
"min": -0.01777919940650463,
"max": 0.23576189577579498,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.747045993804932,
"min": -4.747045993804932,
"max": 56.582855224609375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0657795076466365,
"min": 0.06551669819195069,
"max": 0.07362651490003835,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.920913107052911,
"min": 0.4741019534369283,
"max": 1.0415834163717341,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0119709899313637,
"min": 0.00024015565476502205,
"max": 0.0119709899313637,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1675938590390918,
"min": 0.0031220235119452868,
"max": 0.1675938590390918,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.71230457212143e-06,
"min": 7.71230457212143e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010797226400970002,
"min": 0.00010797226400970002,
"max": 0.0032600510133164,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257073571428574,
"min": 0.10257073571428574,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359903000000003,
"min": 1.3691136000000002,
"max": 2.4424995000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000266816497857143,
"min": 0.000266816497857143,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003735430970000002,
"min": 0.003735430970000002,
"max": 0.10868969164,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01283484511077404,
"min": 0.01283484511077404,
"max": 0.44461163878440857,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17968782782554626,
"min": 0.17968782782554626,
"max": 3.112281560897827,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 498.8636363636364,
"min": 475.73015873015873,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32925.0,
"min": 15984.0,
"max": 32925.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3495848140481748,
"min": -1.0000000521540642,
"max": 1.3495848140481748,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 89.07259772717953,
"min": -32.000001668930054,
"max": 89.07259772717953,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3495848140481748,
"min": -1.0000000521540642,
"max": 1.3495848140481748,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 89.07259772717953,
"min": -32.000001668930054,
"max": 89.07259772717953,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06561187095675533,
"min": 0.06458183616193729,
"max": 9.70235175266862,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.330383483145852,
"min": 3.862981271435274,
"max": 155.2376280426979,
"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": "1711430820",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711432867"
},
"total": 2046.691266546,
"count": 1,
"self": 0.492889608999576,
"children": {
"run_training.setup": {
"total": 0.05448556800001825,
"count": 1,
"self": 0.05448556800001825
},
"TrainerController.start_learning": {
"total": 2046.1438913690004,
"count": 1,
"self": 1.2627557039945714,
"children": {
"TrainerController._reset_env": {
"total": 2.8627137040000434,
"count": 1,
"self": 2.8627137040000434
},
"TrainerController.advance": {
"total": 2041.9333631800057,
"count": 63438,
"self": 1.307645699997238,
"children": {
"env_step": {
"total": 1435.8775129540304,
"count": 63438,
"self": 1311.088507581982,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.03671741399319,
"count": 63438,
"self": 4.408021188929297,
"children": {
"TorchPolicy.evaluate": {
"total": 119.62869622506389,
"count": 62568,
"self": 119.62869622506389
}
}
},
"workers": {
"total": 0.7522879580553763,
"count": 63438,
"self": 0.0,
"children": {
"worker_root": {
"total": 2041.4508641400025,
"count": 63438,
"is_parallel": true,
"self": 842.7531033170412,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008067167000035624,
"count": 1,
"is_parallel": true,
"self": 0.004154675999984647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003912491000050977,
"count": 8,
"is_parallel": true,
"self": 0.003912491000050977
}
}
},
"UnityEnvironment.step": {
"total": 0.05615486800002145,
"count": 1,
"is_parallel": true,
"self": 0.000626987999908124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004410920000736951,
"count": 1,
"is_parallel": true,
"self": 0.0004410920000736951
},
"communicator.exchange": {
"total": 0.05337200799999664,
"count": 1,
"is_parallel": true,
"self": 0.05337200799999664
},
"steps_from_proto": {
"total": 0.0017147800000429925,
"count": 1,
"is_parallel": true,
"self": 0.00033868200000597426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013760980000370182,
"count": 8,
"is_parallel": true,
"self": 0.0013760980000370182
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1198.6977608229613,
"count": 63437,
"is_parallel": true,
"self": 32.91084899401676,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.392108971969606,
"count": 63437,
"is_parallel": true,
"self": 22.392108971969606
},
"communicator.exchange": {
"total": 1048.875168481983,
"count": 63437,
"is_parallel": true,
"self": 1048.875168481983
},
"steps_from_proto": {
"total": 94.51963437499171,
"count": 63437,
"is_parallel": true,
"self": 18.381173029914635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.13846134507708,
"count": 507496,
"is_parallel": true,
"self": 76.13846134507708
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 604.7482045259782,
"count": 63438,
"self": 2.39615101889774,
"children": {
"process_trajectory": {
"total": 119.46119962108264,
"count": 63438,
"self": 119.16669903308252,
"children": {
"RLTrainer._checkpoint": {
"total": 0.294500588000119,
"count": 2,
"self": 0.294500588000119
}
}
},
"_update_policy": {
"total": 482.8908538859978,
"count": 441,
"self": 280.53569026699654,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.35516361900125,
"count": 22833,
"self": 202.35516361900125
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3060002856946085e-06,
"count": 1,
"self": 1.3060002856946085e-06
},
"TrainerController._save_models": {
"total": 0.08505747499975769,
"count": 1,
"self": 0.0014149179996820749,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08364255700007561,
"count": 1,
"self": 0.08364255700007561
}
}
}
}
}
}
}