arbts
wider net
1174298
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14911867678165436,
"min": 0.14457976818084717,
"max": 1.357846975326538,
"count": 50
},
"Pyramids.Policy.Entropy.sum": {
"value": 4440.15771484375,
"min": 4318.88671875,
"max": 41191.64453125,
"count": 50
},
"Pyramids.Step.mean": {
"value": 1499978.0,
"min": 29957.0,
"max": 1499978.0,
"count": 50
},
"Pyramids.Step.sum": {
"value": 1499978.0,
"min": 29957.0,
"max": 1499978.0,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7336004972457886,
"min": -0.09463340789079666,
"max": 0.8542152643203735,
"count": 50
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 212.744140625,
"min": -22.806652069091797,
"max": 261.3898620605469,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02970135398209095,
"min": -0.005458368919789791,
"max": 0.3286758065223694,
"count": 50
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.61339282989502,
"min": -1.599302053451538,
"max": 78.88219451904297,
"count": 50
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0688148987909598,
"min": 0.06564255493659792,
"max": 0.07551408395242559,
"count": 50
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.032223481864397,
"min": 0.6041126716194047,
"max": 1.0840472226480808,
"count": 50
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015034020498084527,
"min": 0.0005084901191079379,
"max": 0.016872440763455374,
"count": 50
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2255103074712679,
"min": 0.006610371548403193,
"max": 0.23621417068837525,
"count": 50
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.004054554764452e-06,
"min": 5.004054554764452e-06,
"max": 0.0004944501677766333,
"count": 50
},
"Pyramids.Policy.LearningRate.sum": {
"value": 7.506081832146677e-05,
"min": 7.506081832146677e-05,
"max": 0.006372491458835066,
"count": 50
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10100079111111111,
"min": 0.10100079111111111,
"max": 0.19889003333333333,
"count": 50
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5150118666666668,
"min": 1.442476466666667,
"max": 2.6744982666666677,
"count": 50
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00010997903200000013,
"min": 0.00010997903200000013,
"max": 0.00988911433,
"count": 50
},
"Pyramids.Policy.Beta.sum": {
"value": 0.001649685480000002,
"min": 0.001649685480000002,
"max": 0.12746237684,
"count": 50
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009963830932974815,
"min": 0.009886900894343853,
"max": 0.5029244422912598,
"count": 50
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14945746958255768,
"min": 0.14202284812927246,
"max": 4.023395538330078,
"count": 50
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 269.76521739130436,
"min": 219.53333333333333,
"max": 990.40625,
"count": 50
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31023.0,
"min": 17011.0,
"max": 32680.0,
"count": 50
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7128365074810774,
"min": -0.9288438011426479,
"max": 1.7656503525045184,
"count": 50
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 196.9761983603239,
"min": -30.332601636648178,
"max": 238.36279758810997,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7128365074810774,
"min": -0.9288438011426479,
"max": 1.7656503525045184,
"count": 50
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 196.9761983603239,
"min": -30.332601636648178,
"max": 238.36279758810997,
"count": 50
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.027769504379703786,
"min": 0.023049835703568534,
"max": 9.131448575192028,
"count": 50
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.1934930036659352,
"min": 3.0712533583136974,
"max": 164.3660743534565,
"count": 50
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680448692",
"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 --force",
"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": "1680453710"
},
"total": 5018.692688668001,
"count": 1,
"self": 0.548608127000989,
"children": {
"run_training.setup": {
"total": 0.13231575999998313,
"count": 1,
"self": 0.13231575999998313
},
"TrainerController.start_learning": {
"total": 5018.011764781,
"count": 1,
"self": 3.7097439110002597,
"children": {
"TrainerController._reset_env": {
"total": 0.974192026998935,
"count": 1,
"self": 0.974192026998935
},
"TrainerController.advance": {
"total": 5013.236825741,
"count": 97153,
"self": 3.884431190734176,
"children": {
"env_step": {
"total": 3665.302144066216,
"count": 97153,
"self": 3484.3424853444085,
"children": {
"SubprocessEnvManager._take_step": {
"total": 178.66473442416827,
"count": 97153,
"self": 10.231611608138337,
"children": {
"TorchPolicy.evaluate": {
"total": 168.43312281602994,
"count": 93799,
"self": 168.43312281602994
}
}
},
"workers": {
"total": 2.294924297639227,
"count": 97153,
"self": 0.0,
"children": {
"worker_root": {
"total": 5006.905717242915,
"count": 97153,
"is_parallel": true,
"self": 1783.2099591331516,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020532819999061758,
"count": 1,
"is_parallel": true,
"self": 0.0006697109965898562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013835710033163195,
"count": 8,
"is_parallel": true,
"self": 0.0013835710033163195
}
}
},
"UnityEnvironment.step": {
"total": 0.06110375200114504,
"count": 1,
"is_parallel": true,
"self": 0.0006639409984927624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005446970008051721,
"count": 1,
"is_parallel": true,
"self": 0.0005446970008051721
},
"communicator.exchange": {
"total": 0.057912956001018756,
"count": 1,
"is_parallel": true,
"self": 0.057912956001018756
},
"steps_from_proto": {
"total": 0.001982158000828349,
"count": 1,
"is_parallel": true,
"self": 0.0004764660006912891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00150569200013706,
"count": 8,
"is_parallel": true,
"self": 0.00150569200013706
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3223.695758109763,
"count": 97152,
"is_parallel": true,
"self": 68.59751520758982,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 40.04533783928855,
"count": 97152,
"is_parallel": true,
"self": 40.04533783928855
},
"communicator.exchange": {
"total": 2916.729076539945,
"count": 97152,
"is_parallel": true,
"self": 2916.729076539945
},
"steps_from_proto": {
"total": 198.32382852293995,
"count": 97152,
"is_parallel": true,
"self": 45.45018446449649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 152.87364405844346,
"count": 777216,
"is_parallel": true,
"self": 152.87364405844346
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1344.0502504840497,
"count": 97153,
"self": 7.365678050149654,
"children": {
"process_trajectory": {
"total": 202.18086992790268,
"count": 97153,
"self": 201.8194016569032,
"children": {
"RLTrainer._checkpoint": {
"total": 0.36146827099946677,
"count": 3,
"self": 0.36146827099946677
}
}
},
"_update_policy": {
"total": 1134.5037025059974,
"count": 697,
"self": 596.8407815309984,
"children": {
"TorchPPOOptimizer.update": {
"total": 537.662920974999,
"count": 34209,
"self": 537.662920974999
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4600009308196604e-06,
"count": 1,
"self": 1.4600009308196604e-06
},
"TrainerController._save_models": {
"total": 0.09100164200026484,
"count": 1,
"self": 0.0021150920019863406,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0888865499982785,
"count": 1,
"self": 0.0888865499982785
}
}
}
}
}
}
}