u79jm's picture
First Push
ca10db3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.47604280710220337,
"min": 0.47604280710220337,
"max": 1.4446613788604736,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14212.734375,
"min": 14212.734375,
"max": 43825.24609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989941.0,
"min": 29929.0,
"max": 989941.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989941.0,
"min": 29929.0,
"max": 989941.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4988465905189514,
"min": -0.10815329849720001,
"max": 0.6467155814170837,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 137.68165588378906,
"min": -26.064945220947266,
"max": 183.0205078125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.019024966284632683,
"min": -0.0847652330994606,
"max": 0.4699549973011017,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -5.250890731811523,
"min": -22.462787628173828,
"max": 111.37933349609375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06557454846972856,
"min": 0.06557454846972856,
"max": 0.07610911399838405,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9180436785761997,
"min": 0.5755236836220345,
"max": 1.0868499399415061,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017109893659771818,
"min": 0.0005310243234576943,
"max": 0.017391231522951,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23953851123680545,
"min": 0.005841267558034637,
"max": 0.24961079847707884,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.532947489050001e-06,
"min": 7.532947489050001e-06,
"max": 0.0002948425892191375,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010546126484670002,
"min": 0.00010546126484670002,
"max": 0.0033837716720762,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251095000000002,
"min": 0.10251095000000002,
"max": 0.1982808625,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351533000000003,
"min": 1.4351533000000003,
"max": 2.5279238,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002608439050000001,
"min": 0.0002608439050000001,
"max": 0.009828258163749999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003651814670000001,
"min": 0.003651814670000001,
"max": 0.11281958762000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010522930882871151,
"min": 0.010522930882871151,
"max": 0.5509496331214905,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14732103049755096,
"min": 0.14732103049755096,
"max": 4.407597064971924,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 357.51190476190476,
"min": 286.59183673469386,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30031.0,
"min": 16472.0,
"max": 31987.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.428116643446542,
"min": -0.9998875516466796,
"max": 1.6725252344451769,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 119.96179804950953,
"min": -31.99640165269375,
"max": 165.90279834717512,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.428116643446542,
"min": -0.9998875516466796,
"max": 1.6725252344451769,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 119.96179804950953,
"min": -31.99640165269375,
"max": 165.90279834717512,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03912227700844336,
"min": 0.03317278656535876,
"max": 11.226031327072311,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2862712687092426,
"min": 3.2841058699705172,
"max": 190.8425325602293,
"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": "1738559307",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738561624"
},
"total": 2317.53693054,
"count": 1,
"self": 0.6387757509992298,
"children": {
"run_training.setup": {
"total": 0.020488311000008252,
"count": 1,
"self": 0.020488311000008252
},
"TrainerController.start_learning": {
"total": 2316.8776664780007,
"count": 1,
"self": 1.2325307620758394,
"children": {
"TrainerController._reset_env": {
"total": 2.782481935000078,
"count": 1,
"self": 2.782481935000078
},
"TrainerController.advance": {
"total": 2312.7737902359245,
"count": 63963,
"self": 1.3038043139463298,
"children": {
"env_step": {
"total": 1611.555079692996,
"count": 63963,
"self": 1461.0557054300277,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.7474469280021,
"count": 63963,
"self": 4.4858105300443185,
"children": {
"TorchPolicy.evaluate": {
"total": 145.26163639795777,
"count": 62576,
"self": 145.26163639795777
}
}
},
"workers": {
"total": 0.7519273349662399,
"count": 63963,
"self": 0.0,
"children": {
"worker_root": {
"total": 2311.900828937956,
"count": 63963,
"is_parallel": true,
"self": 961.8594046509472,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003938794000077905,
"count": 1,
"is_parallel": true,
"self": 0.0008425030000580591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030962910000198463,
"count": 8,
"is_parallel": true,
"self": 0.0030962910000198463
}
}
},
"UnityEnvironment.step": {
"total": 0.09318775299993831,
"count": 1,
"is_parallel": true,
"self": 0.0005495689999861497,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005917979999594536,
"count": 1,
"is_parallel": true,
"self": 0.0005917979999594536
},
"communicator.exchange": {
"total": 0.08993970200003787,
"count": 1,
"is_parallel": true,
"self": 0.08993970200003787
},
"steps_from_proto": {
"total": 0.0021066839999548392,
"count": 1,
"is_parallel": true,
"self": 0.0004346989996975026,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016719850002573367,
"count": 8,
"is_parallel": true,
"self": 0.0016719850002573367
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1350.0414242870086,
"count": 63962,
"is_parallel": true,
"self": 31.746018937109966,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.932072657983326,
"count": 63962,
"is_parallel": true,
"self": 22.932072657983326
},
"communicator.exchange": {
"total": 1201.1590488099532,
"count": 63962,
"is_parallel": true,
"self": 1201.1590488099532
},
"steps_from_proto": {
"total": 94.20428388196206,
"count": 63962,
"is_parallel": true,
"self": 18.403628280920884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.80065560104117,
"count": 511696,
"is_parallel": true,
"self": 75.80065560104117
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 699.9149062289823,
"count": 63963,
"self": 2.4266725540251173,
"children": {
"process_trajectory": {
"total": 129.83864057896108,
"count": 63963,
"self": 129.58002843796157,
"children": {
"RLTrainer._checkpoint": {
"total": 0.258612140999503,
"count": 2,
"self": 0.258612140999503
}
}
},
"_update_policy": {
"total": 567.6495930959961,
"count": 452,
"self": 312.7086374859923,
"children": {
"TorchPPOOptimizer.update": {
"total": 254.9409556100038,
"count": 22818,
"self": 254.9409556100038
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.160004654200748e-07,
"count": 1,
"self": 8.160004654200748e-07
},
"TrainerController._save_models": {
"total": 0.08886272899962933,
"count": 1,
"self": 0.0014124729996183305,
"children": {
"RLTrainer._checkpoint": {
"total": 0.087450256000011,
"count": 1,
"self": 0.087450256000011
}
}
}
}
}
}
}