danieliser's picture
First Push
71e9197
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5043679475784302,
"min": 0.41905391216278076,
"max": 1.3936951160430908,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15139.1083984375,
"min": 12705.71484375,
"max": 42279.13671875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989996.0,
"min": 29952.0,
"max": 989996.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989996.0,
"min": 29952.0,
"max": 989996.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5681384801864624,
"min": -0.08858076483011246,
"max": 0.5681384801864624,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 154.53366088867188,
"min": -21.259384155273438,
"max": 154.53366088867188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.031010378152132034,
"min": -0.0024092632811516523,
"max": 0.5547972321510315,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.434823036193848,
"min": -0.6480917930603027,
"max": 131.4869384765625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07027631320432025,
"min": 0.06568383957362837,
"max": 0.07498807243604823,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9838683848604834,
"min": 0.4857053958734594,
"max": 1.0511210327591365,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017083019919311777,
"min": 0.0002849375620034061,
"max": 0.01778657109112135,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23916227887036487,
"min": 0.0019945629340238427,
"max": 0.2585412024434168,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.5277311757992857e-05,
"min": 2.5277311757992857e-05,
"max": 0.0009838354301878855,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003538823646119,
"min": 0.0003538823646119,
"max": 0.011690931230906901,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252772142857144,
"min": 0.10252772142857144,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353881000000002,
"min": 1.3691136000000002,
"max": 2.5690931000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002625193707142857,
"min": 0.0002625193707142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00367527119,
"min": 0.00367527119,
"max": 0.11693240069,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013367981649935246,
"min": 0.013367981649935246,
"max": 0.608972430229187,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1871517449617386,
"min": 0.1871517449617386,
"max": 4.2628068923950195,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 332.14942528735634,
"min": 332.14942528735634,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28897.0,
"min": 15984.0,
"max": 32292.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6209906796210034,
"min": -1.0000000521540642,
"max": 1.6209906796210034,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 139.4051984474063,
"min": -32.000001668930054,
"max": 141.80299772322178,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6209906796210034,
"min": -1.0000000521540642,
"max": 1.6209906796210034,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 139.4051984474063,
"min": -32.000001668930054,
"max": 141.80299772322178,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04579534912739101,
"min": 0.04579534912739101,
"max": 13.14712281152606,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.9384000249556266,
"min": 3.9384000249556266,
"max": 210.35396498441696,
"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": "1685394507",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685396718"
},
"total": 2211.740751886,
"count": 1,
"self": 0.8415721949986619,
"children": {
"run_training.setup": {
"total": 0.04753148700001475,
"count": 1,
"self": 0.04753148700001475
},
"TrainerController.start_learning": {
"total": 2210.8516482040013,
"count": 1,
"self": 1.2716093523449672,
"children": {
"TrainerController._reset_env": {
"total": 3.8744662499993865,
"count": 1,
"self": 3.8744662499993865
},
"TrainerController.advance": {
"total": 2205.503797262658,
"count": 63623,
"self": 1.336419953388031,
"children": {
"env_step": {
"total": 1540.1381441607627,
"count": 63623,
"self": 1428.4563610835576,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.93053759634859,
"count": 63623,
"self": 4.686765850374286,
"children": {
"TorchPolicy.evaluate": {
"total": 106.2437717459743,
"count": 62565,
"self": 106.2437717459743
}
}
},
"workers": {
"total": 0.7512454808565963,
"count": 63623,
"self": 0.0,
"children": {
"worker_root": {
"total": 2205.855746256748,
"count": 63623,
"is_parallel": true,
"self": 887.7565923366255,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019239749999542255,
"count": 1,
"is_parallel": true,
"self": 0.0005886359977012035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001335339002253022,
"count": 8,
"is_parallel": true,
"self": 0.001335339002253022
}
}
},
"UnityEnvironment.step": {
"total": 0.05059424000137369,
"count": 1,
"is_parallel": true,
"self": 0.000584316001550178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005033569996157894,
"count": 1,
"is_parallel": true,
"self": 0.0005033569996157894
},
"communicator.exchange": {
"total": 0.047371499000291806,
"count": 1,
"is_parallel": true,
"self": 0.047371499000291806
},
"steps_from_proto": {
"total": 0.0021350679999159183,
"count": 1,
"is_parallel": true,
"self": 0.0003901070012943819,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017449609986215364,
"count": 8,
"is_parallel": true,
"self": 0.0017449609986215364
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1318.0991539201223,
"count": 63622,
"is_parallel": true,
"self": 34.00667230367253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.07370115779122,
"count": 63622,
"is_parallel": true,
"self": 23.07370115779122
},
"communicator.exchange": {
"total": 1156.6628743428137,
"count": 63622,
"is_parallel": true,
"self": 1156.6628743428137
},
"steps_from_proto": {
"total": 104.35590611584485,
"count": 63622,
"is_parallel": true,
"self": 20.29828629122676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.05761982461809,
"count": 508976,
"is_parallel": true,
"self": 84.05761982461809
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 664.029233148507,
"count": 63623,
"self": 2.374158520351557,
"children": {
"process_trajectory": {
"total": 109.10068938615404,
"count": 63623,
"self": 108.75397265815263,
"children": {
"RLTrainer._checkpoint": {
"total": 0.34671672800141096,
"count": 2,
"self": 0.34671672800141096
}
}
},
"_update_policy": {
"total": 552.5543852420014,
"count": 443,
"self": 343.60553028598406,
"children": {
"TorchPPOOptimizer.update": {
"total": 208.94885495601739,
"count": 22776,
"self": 208.94885495601739
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2969994713785127e-06,
"count": 1,
"self": 1.2969994713785127e-06
},
"TrainerController._save_models": {
"total": 0.20177404199966986,
"count": 1,
"self": 0.002894191000450519,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19887985099921934,
"count": 1,
"self": 0.19887985099921934
}
}
}
}
}
}
}