ppo-PyramidsRND / run_logs /timers.json
mahdisf's picture
First Push
c8fcf33 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.17609797418117523,
"min": 0.17609797418117523,
"max": 1.4335333108901978,
"count": 70
},
"Pyramids.Policy.Entropy.sum": {
"value": 5297.02685546875,
"min": 5297.02685546875,
"max": 43487.66796875,
"count": 70
},
"Pyramids.Step.mean": {
"value": 2099976.0,
"min": 29952.0,
"max": 2099976.0,
"count": 70
},
"Pyramids.Step.sum": {
"value": 2099976.0,
"min": 29952.0,
"max": 2099976.0,
"count": 70
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8246182203292847,
"min": -0.08442184329032898,
"max": 0.8569663763046265,
"count": 70
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 247.38546752929688,
"min": -20.261241912841797,
"max": 261.309326171875,
"count": 70
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004147369880229235,
"min": -0.01478775218129158,
"max": 0.44796276092529297,
"count": 70
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.244210958480835,
"min": -4.229297161102295,
"max": 108.85494995117188,
"count": 70
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07028471326387972,
"min": 0.06562414554701676,
"max": 0.07659768332156262,
"count": 70
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9839859856943162,
"min": 0.5361837832509384,
"max": 1.0719488904384589,
"count": 70
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012771265152131738,
"min": 0.0007328222595278727,
"max": 0.01736652688705363,
"count": 70
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17879771212984433,
"min": 0.00956747708254145,
"max": 0.2604979033058044,
"count": 70
},
"Pyramids.Policy.LearningRate.mean": {
"value": 9.157888375944285e-05,
"min": 9.157888375944285e-05,
"max": 0.00029838354339596195,
"count": 70
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0012821043726322,
"min": 0.0012821043726322,
"max": 0.003969674576775166,
"count": 70
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.13052627142857146,
"min": 0.13052627142857146,
"max": 0.19946118095238097,
"count": 70
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.8273678000000002,
"min": 1.3962282666666668,
"max": 2.782595433333334,
"count": 70
},
"Pyramids.Policy.Beta.mean": {
"value": 0.003059574515714286,
"min": 0.003059574515714286,
"max": 0.009946171977142856,
"count": 70
},
"Pyramids.Policy.Beta.sum": {
"value": 0.042834043220000007,
"min": 0.042834043220000007,
"max": 0.13233016085000002,
"count": 70
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009726569056510925,
"min": 0.009726569056510925,
"max": 0.6236806511878967,
"count": 70
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13617196679115295,
"min": 0.13617196679115295,
"max": 4.365764617919922,
"count": 70
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 222.53676470588235,
"min": 212.61870503597123,
"max": 999.0,
"count": 70
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30265.0,
"min": 15984.0,
"max": 33581.0,
"count": 70
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7480426335926442,
"min": -1.0000000521540642,
"max": 1.7873812792755717,
"count": 70
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 237.7337981685996,
"min": -29.91220163553953,
"max": 254.95139844715595,
"count": 70
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7480426335926442,
"min": -1.0000000521540642,
"max": 1.7873812792755717,
"count": 70
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 237.7337981685996,
"min": -29.91220163553953,
"max": 254.95139844715595,
"count": 70
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.022574970948827447,
"min": 0.02226565197026843,
"max": 13.050121014937758,
"count": 70
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.0701960490405327,
"min": 2.817954811427626,
"max": 208.80193623900414,
"count": 70
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 70
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 70
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1753981802",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/envs/myenv/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1753986861"
},
"total": 5059.247165008999,
"count": 1,
"self": 0.6608996729992214,
"children": {
"run_training.setup": {
"total": 0.018435114000112662,
"count": 1,
"self": 0.018435114000112662
},
"TrainerController.start_learning": {
"total": 5058.567830222,
"count": 1,
"self": 2.8385758361437183,
"children": {
"TrainerController._reset_env": {
"total": 2.277726549000363,
"count": 1,
"self": 2.277726549000363
},
"TrainerController.advance": {
"total": 5053.220863552856,
"count": 136524,
"self": 2.838577322839228,
"children": {
"env_step": {
"total": 3622.5137404318634,
"count": 136524,
"self": 3301.044713032095,
"children": {
"SubprocessEnvManager._take_step": {
"total": 319.8005984847873,
"count": 136524,
"self": 9.73612554267038,
"children": {
"TorchPolicy.evaluate": {
"total": 310.06447294211694,
"count": 131777,
"self": 310.06447294211694
}
}
},
"workers": {
"total": 1.6684289149811775,
"count": 136523,
"self": 0.0,
"children": {
"worker_root": {
"total": 5048.215380574185,
"count": 136523,
"is_parallel": true,
"self": 1984.8738868851847,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020152659999439493,
"count": 1,
"is_parallel": true,
"self": 0.0006587599996237259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013565060003202234,
"count": 8,
"is_parallel": true,
"self": 0.0013565060003202234
}
}
},
"UnityEnvironment.step": {
"total": 0.047719743000016024,
"count": 1,
"is_parallel": true,
"self": 0.0005431100003079337,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044361099980960716,
"count": 1,
"is_parallel": true,
"self": 0.00044361099980960716
},
"communicator.exchange": {
"total": 0.04515590099981637,
"count": 1,
"is_parallel": true,
"self": 0.04515590099981637
},
"steps_from_proto": {
"total": 0.0015771210000821156,
"count": 1,
"is_parallel": true,
"self": 0.00034262800045326003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012344929996288556,
"count": 8,
"is_parallel": true,
"self": 0.0012344929996288556
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3063.341493689,
"count": 136522,
"is_parallel": true,
"self": 67.23209406519663,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 49.52485759689307,
"count": 136522,
"is_parallel": true,
"self": 49.52485759689307
},
"communicator.exchange": {
"total": 2742.9347963909063,
"count": 136522,
"is_parallel": true,
"self": 2742.9347963909063
},
"steps_from_proto": {
"total": 203.6497456360039,
"count": 136522,
"is_parallel": true,
"self": 40.941732780973325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 162.70801285503057,
"count": 1092176,
"is_parallel": true,
"self": 162.70801285503057
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1427.8685457981537,
"count": 136523,
"self": 5.893616583328367,
"children": {
"process_trajectory": {
"total": 279.852703957848,
"count": 136523,
"self": 279.4680087288475,
"children": {
"RLTrainer._checkpoint": {
"total": 0.38469522900049924,
"count": 4,
"self": 0.38469522900049924
}
}
},
"_update_policy": {
"total": 1142.1222252569773,
"count": 981,
"self": 629.7578252680751,
"children": {
"TorchPPOOptimizer.update": {
"total": 512.3643999889023,
"count": 47997,
"self": 512.3643999889023
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.276999682886526e-06,
"count": 1,
"self": 1.276999682886526e-06
},
"TrainerController._save_models": {
"total": 0.23066300700065767,
"count": 1,
"self": 0.003566757000044163,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2270962500006135,
"count": 1,
"self": 0.2270962500006135
}
}
}
}
}
}
}