bonadio's picture
My First Push
76f76ad
raw
history blame contribute delete
No virus
19.1 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4290629029273987,
"min": 0.4290629029273987,
"max": 1.446290373802185,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12940.537109375,
"min": 12940.537109375,
"max": 43874.6640625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989964.0,
"min": 29952.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989964.0,
"min": 29952.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.06382940709590912,
"min": -0.09052539616823196,
"max": 0.12774768471717834,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 15.829692840576172,
"min": -21.816619873046875,
"max": 31.936920166015625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.05865363031625748,
"min": 0.05607644468545914,
"max": 0.536797285079956,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 14.546100616455078,
"min": 14.019111633300781,
"max": 127.22096252441406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06912498022202195,
"min": 0.06609567225898007,
"max": 0.07425339419891373,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9677497231083073,
"min": 0.474642474018305,
"max": 1.0721870370154434,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005070632323829059,
"min": 0.00023955306936388604,
"max": 0.007977470812745326,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.07098885253360683,
"min": 0.0028746368323666325,
"max": 0.10849563195006338,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.419247526949999e-06,
"min": 7.419247526949999e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010386946537729999,
"min": 0.00010386946537729999,
"max": 0.0033309045896984996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247305000000002,
"min": 0.10247305000000002,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4346227000000003,
"min": 1.3691136000000002,
"max": 2.4824236000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000257057695,
"min": 0.000257057695,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00359880773,
"min": 0.00359880773,
"max": 0.11103911985,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.055778712034225464,
"min": 0.05370231345295906,
"max": 0.41393327713012695,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.7809019684791565,
"min": 0.7518323659896851,
"max": 2.8975329399108887,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 830.5,
"min": 697.6888888888889,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31559.0,
"min": 15984.0,
"max": 33147.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.011194697336146706,
"min": -1.0000000521540642,
"max": 0.4367761548076357,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 0.42539849877357483,
"min": -32.000001668930054,
"max": 18.3445985019207,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.011194697336146706,
"min": -1.0000000521540642,
"max": 0.4367761548076357,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 0.42539849877357483,
"min": -32.000001668930054,
"max": 18.3445985019207,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.4580868245255643,
"min": 0.3895432891117202,
"max": 7.958575043827295,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 17.407299331971444,
"min": 16.44805741321761,
"max": 127.33720070123672,
"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": "1674754628",
"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": "1.21.6",
"end_time_seconds": "1674756547"
},
"total": 1918.1737377739998,
"count": 1,
"self": 0.4442435299997669,
"children": {
"run_training.setup": {
"total": 0.11675340699997605,
"count": 1,
"self": 0.11675340699997605
},
"TrainerController.start_learning": {
"total": 1917.612740837,
"count": 1,
"self": 1.0815145040216976,
"children": {
"TrainerController._reset_env": {
"total": 9.41590054400001,
"count": 1,
"self": 9.41590054400001
},
"TrainerController.advance": {
"total": 1907.0343472409784,
"count": 63248,
"self": 1.2004467230058253,
"children": {
"env_step": {
"total": 1262.3299688100392,
"count": 63248,
"self": 1162.8677429250924,
"children": {
"SubprocessEnvManager._take_step": {
"total": 98.77711450295374,
"count": 63248,
"self": 4.125079918000097,
"children": {
"TorchPolicy.evaluate": {
"total": 94.65203458495364,
"count": 62555,
"self": 31.7860539599842,
"children": {
"TorchPolicy.sample_actions": {
"total": 62.86598062496944,
"count": 62555,
"self": 62.86598062496944
}
}
}
}
},
"workers": {
"total": 0.6851113819931243,
"count": 63248,
"self": 0.0,
"children": {
"worker_root": {
"total": 1914.5272117979932,
"count": 63248,
"is_parallel": true,
"self": 843.2165945599722,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011103618000049664,
"count": 1,
"is_parallel": true,
"self": 0.00512042500008647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005983192999963194,
"count": 8,
"is_parallel": true,
"self": 0.005983192999963194
}
}
},
"UnityEnvironment.step": {
"total": 0.04752274800000578,
"count": 1,
"is_parallel": true,
"self": 0.000500639999984287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004401820000339285,
"count": 1,
"is_parallel": true,
"self": 0.0004401820000339285
},
"communicator.exchange": {
"total": 0.04503178200002367,
"count": 1,
"is_parallel": true,
"self": 0.04503178200002367
},
"steps_from_proto": {
"total": 0.0015501439999638933,
"count": 1,
"is_parallel": true,
"self": 0.0003792439999301678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011709000000337255,
"count": 8,
"is_parallel": true,
"self": 0.0011709000000337255
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1071.310617238021,
"count": 63247,
"is_parallel": true,
"self": 27.25530864609391,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.3596326800062,
"count": 63247,
"is_parallel": true,
"self": 21.3596326800062
},
"communicator.exchange": {
"total": 935.3382033999767,
"count": 63247,
"is_parallel": true,
"self": 935.3382033999767
},
"steps_from_proto": {
"total": 87.3574725119442,
"count": 63247,
"is_parallel": true,
"self": 19.9720697349116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.3854027770326,
"count": 505976,
"is_parallel": true,
"self": 67.3854027770326
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 643.5039317079334,
"count": 63248,
"self": 2.114259977953452,
"children": {
"process_trajectory": {
"total": 138.08053947198215,
"count": 63248,
"self": 137.90069007598214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1798493960000087,
"count": 2,
"self": 0.1798493960000087
}
}
},
"_update_policy": {
"total": 503.30913225799776,
"count": 445,
"self": 188.96102759600882,
"children": {
"TorchPPOOptimizer.update": {
"total": 314.34810466198894,
"count": 22815,
"self": 314.34810466198894
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1629999789875e-06,
"count": 1,
"self": 1.1629999789875e-06
},
"TrainerController._save_models": {
"total": 0.08097738500009655,
"count": 1,
"self": 0.001411217000168108,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07956616799992844,
"count": 1,
"self": 0.07956616799992844
}
}
}
}
}
}
}