CoreyMorris's picture
first model
2214178
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5968920588493347,
"min": 0.5968920588493347,
"max": 1.472550392150879,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17973.61328125,
"min": 17973.61328125,
"max": 44671.2890625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989980.0,
"min": 29952.0,
"max": 989980.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989980.0,
"min": 29952.0,
"max": 989980.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.38819900155067444,
"min": -0.09489074349403381,
"max": 0.41657599806785583,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 104.81372833251953,
"min": -22.67888832092285,
"max": 111.22579193115234,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.018253551796078682,
"min": -0.014444096013903618,
"max": 0.2372073382139206,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.928459167480469,
"min": -3.726576805114746,
"max": 56.40264892578125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06692978520428465,
"min": 0.06486947859784345,
"max": 0.0730705349022484,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9370169928599851,
"min": 0.47909443903528426,
"max": 1.0573918642670228,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013248839467448486,
"min": 0.0002418285690092009,
"max": 0.013248839467448486,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18548375254427882,
"min": 0.0031437713971196116,
"max": 0.19261469080326304,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4004332475071435e-06,
"min": 7.4004332475071435e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010360606546510001,
"min": 0.00010360606546510001,
"max": 0.0032522474159175996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10246677857142857,
"min": 0.10246677857142857,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4345348999999998,
"min": 1.3691136000000002,
"max": 2.4008334000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025643117928571437,
"min": 0.00025643117928571437,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003590036510000001,
"min": 0.003590036510000001,
"max": 0.10842983176000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011455679312348366,
"min": 0.011247391812503338,
"max": 0.3264869153499603,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16037951409816742,
"min": 0.15746349096298218,
"max": 2.2854084968566895,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 416.95588235294116,
"min": 416.95588235294116,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28353.0,
"min": 15984.0,
"max": 33111.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.465358801514787,
"min": -1.0000000521540642,
"max": 1.465358801514787,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 99.6443985030055,
"min": -32.000001668930054,
"max": 99.6443985030055,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.465358801514787,
"min": -1.0000000521540642,
"max": 1.465358801514787,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 99.6443985030055,
"min": -32.000001668930054,
"max": 99.6443985030055,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.050207778835422635,
"min": 0.0492561225916302,
"max": 6.339831321500242,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.414128960808739,
"min": 3.414128960808739,
"max": 101.43730114400387,
"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": "1673453026",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1.21.6",
"end_time_seconds": "1673455043"
},
"total": 2016.323672298,
"count": 1,
"self": 0.4246031689999654,
"children": {
"run_training.setup": {
"total": 0.12404593799999475,
"count": 1,
"self": 0.12404593799999475
},
"TrainerController.start_learning": {
"total": 2015.775023191,
"count": 1,
"self": 1.3299447780480023,
"children": {
"TrainerController._reset_env": {
"total": 7.002533541000048,
"count": 1,
"self": 7.002533541000048
},
"TrainerController.advance": {
"total": 2007.3514864569518,
"count": 63492,
"self": 1.4162239269564907,
"children": {
"env_step": {
"total": 1341.853429957008,
"count": 63492,
"self": 1232.0933438289994,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.93913530103202,
"count": 63492,
"self": 4.51441962705735,
"children": {
"TorchPolicy.evaluate": {
"total": 104.42471567397467,
"count": 62553,
"self": 34.965732511945816,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.45898316202886,
"count": 62553,
"self": 69.45898316202886
}
}
}
}
},
"workers": {
"total": 0.8209508269765138,
"count": 63492,
"self": 0.0,
"children": {
"worker_root": {
"total": 2011.5864757039928,
"count": 63492,
"is_parallel": true,
"self": 882.3824782920126,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005979062000051272,
"count": 1,
"is_parallel": true,
"self": 0.003712761000087994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022663009999632777,
"count": 8,
"is_parallel": true,
"self": 0.0022663009999632777
}
}
},
"UnityEnvironment.step": {
"total": 0.046775289000038356,
"count": 1,
"is_parallel": true,
"self": 0.0005351090001113334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004700409999713884,
"count": 1,
"is_parallel": true,
"self": 0.0004700409999713884
},
"communicator.exchange": {
"total": 0.04406868699993538,
"count": 1,
"is_parallel": true,
"self": 0.04406868699993538
},
"steps_from_proto": {
"total": 0.0017014520000202538,
"count": 1,
"is_parallel": true,
"self": 0.00044917699995039584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001252275000069858,
"count": 8,
"is_parallel": true,
"self": 0.001252275000069858
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1129.2039974119803,
"count": 63491,
"is_parallel": true,
"self": 28.66685668194168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.34356911101463,
"count": 63491,
"is_parallel": true,
"self": 24.34356911101463
},
"communicator.exchange": {
"total": 968.5192893090042,
"count": 63491,
"is_parallel": true,
"self": 968.5192893090042
},
"steps_from_proto": {
"total": 107.67428231001963,
"count": 63491,
"is_parallel": true,
"self": 23.782518103046755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.89176420697288,
"count": 507928,
"is_parallel": true,
"self": 83.89176420697288
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 664.0818325729871,
"count": 63492,
"self": 2.348080875989467,
"children": {
"process_trajectory": {
"total": 150.6447423070017,
"count": 63492,
"self": 150.43830613200157,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20643617500013534,
"count": 2,
"self": 0.20643617500013534
}
}
},
"_update_policy": {
"total": 511.0890093899959,
"count": 440,
"self": 197.57362248900995,
"children": {
"TorchPPOOptimizer.update": {
"total": 313.51538690098596,
"count": 22779,
"self": 313.51538690098596
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.030000001075678e-07,
"count": 1,
"self": 9.030000001075678e-07
},
"TrainerController._save_models": {
"total": 0.09105751200013401,
"count": 1,
"self": 0.0013368950003496138,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0897206169997844,
"count": 1,
"self": 0.0897206169997844
}
}
}
}
}
}
}