ppo-PyramidsRND / run_logs /timers.json
ShuchengLi's picture
Initial push for Pyramids Training result.
d2be5f1 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.39001962542533875,
"min": 0.3767455220222473,
"max": 1.5890337228775024,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11706.8291015625,
"min": 11392.7841796875,
"max": 48204.92578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989887.0,
"min": 29952.0,
"max": 989887.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989887.0,
"min": 29952.0,
"max": 989887.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3738618791103363,
"min": -0.08232583105564117,
"max": 0.393937349319458,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 100.94271087646484,
"min": -19.9228515625,
"max": 105.31327056884766,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.17826418578624725,
"min": 0.17826418578624725,
"max": 2.9966375827789307,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 48.13132858276367,
"min": 48.13132858276367,
"max": 722.1896362304688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07012641581370392,
"min": 0.06623246054029247,
"max": 0.07618483270958272,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.21037924744111175,
"min": 0.13246492108058494,
"max": 0.22855449812874817,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01532926576619502,
"min": 0.0024635436311655212,
"max": 0.530256910209534,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.04598779729858506,
"min": 0.006305911423745177,
"max": 1.060513820419068,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 8.302197232633335e-06,
"min": 8.302197232633335e-06,
"max": 0.000294528001824,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.4906591697900005e-05,
"min": 2.4906591697900005e-05,
"max": 0.0008572821142392999,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10276736666666668,
"min": 0.10276736666666668,
"max": 0.19817600000000002,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.3083021,
"min": 0.22308029999999995,
"max": 0.5857607000000001,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00028645993000000005,
"min": 0.00028645993000000005,
"max": 0.0098177824,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008593797900000002,
"min": 0.0008593797900000002,
"max": 0.02857749393,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016162410378456116,
"min": 0.016162410378456116,
"max": 0.4336625635623932,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.04848723113536835,
"min": 0.033916737884283066,
"max": 0.8673251271247864,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 404.1940298507463,
"min": 404.1940298507463,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27081.0,
"min": 15984.0,
"max": 32664.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4166387839993435,
"min": -1.0000000521540642,
"max": 1.4166387839993435,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 94.91479852795601,
"min": -30.99940161406994,
"max": 97.59419856965542,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4166387839993435,
"min": -1.0000000521540642,
"max": 1.4166387839993435,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 94.91479852795601,
"min": -30.99940161406994,
"max": 97.59419856965542,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.6639312377143929,
"min": 0.6639312377143929,
"max": 137.953186288476,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 44.483392926864326,
"min": 44.483392926864326,
"max": 2207.250980615616,
"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": "1758355714",
"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 --force --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758358025"
},
"total": 2310.9054830470004,
"count": 1,
"self": 0.6272566400002688,
"children": {
"run_training.setup": {
"total": 0.021845363000466023,
"count": 1,
"self": 0.021845363000466023
},
"TrainerController.start_learning": {
"total": 2310.2563810439997,
"count": 1,
"self": 1.7497958601697974,
"children": {
"TrainerController._reset_env": {
"total": 1.983601713999633,
"count": 1,
"self": 1.983601713999633
},
"TrainerController.advance": {
"total": 2306.38949531883,
"count": 63695,
"self": 1.709104347880384,
"children": {
"env_step": {
"total": 1610.9817235830324,
"count": 63695,
"self": 1439.714309345246,
"children": {
"SubprocessEnvManager._take_step": {
"total": 170.2233050568857,
"count": 63695,
"self": 5.450093550967722,
"children": {
"TorchPolicy.evaluate": {
"total": 164.77321150591797,
"count": 62559,
"self": 164.77321150591797
}
}
},
"workers": {
"total": 1.0441091809007048,
"count": 63695,
"self": 0.0,
"children": {
"worker_root": {
"total": 2304.0414825859953,
"count": 63695,
"is_parallel": true,
"self": 993.0557366759558,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002011270000366494,
"count": 1,
"is_parallel": true,
"self": 0.0005981839995001792,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014130860008663149,
"count": 8,
"is_parallel": true,
"self": 0.0014130860008663149
}
}
},
"UnityEnvironment.step": {
"total": 0.04858106299980136,
"count": 1,
"is_parallel": true,
"self": 0.0005312310004228493,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005916190002608346,
"count": 1,
"is_parallel": true,
"self": 0.0005916190002608346
},
"communicator.exchange": {
"total": 0.04578193999986979,
"count": 1,
"is_parallel": true,
"self": 0.04578193999986979
},
"steps_from_proto": {
"total": 0.0016762729992478853,
"count": 1,
"is_parallel": true,
"self": 0.00035678000040206825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001319492998845817,
"count": 8,
"is_parallel": true,
"self": 0.001319492998845817
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1310.9857459100394,
"count": 63694,
"is_parallel": true,
"self": 33.61996053211806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.373926153898537,
"count": 63694,
"is_parallel": true,
"self": 24.373926153898537
},
"communicator.exchange": {
"total": 1149.4874039969782,
"count": 63694,
"is_parallel": true,
"self": 1149.4874039969782
},
"steps_from_proto": {
"total": 103.50445522704467,
"count": 63694,
"is_parallel": true,
"self": 21.581554281491663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.92290094555301,
"count": 509552,
"is_parallel": true,
"self": 81.92290094555301
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 693.6986673879173,
"count": 63695,
"self": 3.277286374907817,
"children": {
"process_trajectory": {
"total": 132.43142251001245,
"count": 63695,
"self": 132.18165475201204,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2497677580004165,
"count": 2,
"self": 0.2497677580004165
}
}
},
"_update_policy": {
"total": 557.9899585029971,
"count": 95,
"self": 314.28927120497974,
"children": {
"TorchPPOOptimizer.update": {
"total": 243.70068729801733,
"count": 23148,
"self": 243.70068729801733
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.618000169401057e-06,
"count": 1,
"self": 1.618000169401057e-06
},
"TrainerController._save_models": {
"total": 0.1334865329999957,
"count": 1,
"self": 0.0019330590002937242,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13155347399970196,
"count": 1,
"self": 0.13155347399970196
}
}
}
}
}
}
}