ppo-Pyramids / run_logs /timers.json
actualbrain's picture
First Push
ab8dc6b verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.15516012907028198,
"min": 0.15516012907028198,
"max": 1.441590428352356,
"count": 60
},
"Pyramids.Policy.Entropy.sum": {
"value": 4684.5947265625,
"min": 4684.5947265625,
"max": 43732.0859375,
"count": 60
},
"Pyramids.Step.mean": {
"value": 1799891.0,
"min": 29977.0,
"max": 1799891.0,
"count": 60
},
"Pyramids.Step.sum": {
"value": 1799891.0,
"min": 29977.0,
"max": 1799891.0,
"count": 60
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.732874870300293,
"min": -0.14343158900737762,
"max": 0.732874870300293,
"count": 60
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 210.3350830078125,
"min": -34.13671875,
"max": 210.3350830078125,
"count": 60
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010336510837078094,
"min": -0.00017044488049577922,
"max": 0.3998706638813019,
"count": 60
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.966578483581543,
"min": -0.048917680978775024,
"max": 95.16921997070312,
"count": 60
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06712313430034557,
"min": 0.0655161562622414,
"max": 0.0731539917996131,
"count": 60
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9397238802048379,
"min": 0.5097635670525928,
"max": 1.088783588847054,
"count": 60
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013134301773832357,
"min": 0.0002593173372364396,
"max": 0.01760839204265115,
"count": 60
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.183880224833653,
"min": 0.002852490709600835,
"max": 0.2465174885971161,
"count": 60
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00012147050950985,
"min": 0.00012147050950985,
"max": 0.0002984124433863286,
"count": 60
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0017005871331379,
"min": 0.0017005871331379,
"max": 0.0038845853051382665,
"count": 60
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.14049015,
"min": 0.14049015,
"max": 0.19947081428571428,
"count": 60
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.9668621000000002,
"min": 1.3962957,
"max": 2.7375688333333335,
"count": 60
},
"Pyramids.Policy.Beta.mean": {
"value": 0.004054965985,
"min": 0.004054965985,
"max": 0.009947134347142856,
"count": 60
},
"Pyramids.Policy.Beta.sum": {
"value": 0.05676952378999999,
"min": 0.05676952378999999,
"max": 0.12949668716,
"count": 60
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006979435216635466,
"min": 0.006979435216635466,
"max": 0.5191302299499512,
"count": 60
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09771209210157394,
"min": 0.09771209210157394,
"max": 3.633911609649658,
"count": 60
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 267.72972972972974,
"min": 267.72972972972974,
"max": 999.0,
"count": 60
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29718.0,
"min": 16520.0,
"max": 32684.0,
"count": 60
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6962252102188162,
"min": -0.9999484390981735,
"max": 1.7070293952437008,
"count": 60
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 188.2809983342886,
"min": -31.998001664876938,
"max": 188.2809983342886,
"count": 60
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6962252102188162,
"min": -0.9999484390981735,
"max": 1.7070293952437008,
"count": 60
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 188.2809983342886,
"min": -31.998001664876938,
"max": 188.2809983342886,
"count": 60
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.019441300500074175,
"min": 0.019441300500074175,
"max": 9.994171965648146,
"count": 60
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.1579843555082334,
"min": 2.147723367670551,
"max": 169.9009234160185,
"count": 60
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720584960",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720589024"
},
"total": 4063.9246144930003,
"count": 1,
"self": 0.3578237930000796,
"children": {
"run_training.setup": {
"total": 0.061070624000024054,
"count": 1,
"self": 0.061070624000024054
},
"TrainerController.start_learning": {
"total": 4063.505720076,
"count": 1,
"self": 2.50016204705571,
"children": {
"TrainerController._reset_env": {
"total": 3.024343798000018,
"count": 1,
"self": 3.024343798000018
},
"TrainerController.advance": {
"total": 4057.845090118945,
"count": 116318,
"self": 2.5567365261499617,
"children": {
"env_step": {
"total": 2910.566632085842,
"count": 116318,
"self": 2675.4829822889046,
"children": {
"SubprocessEnvManager._take_step": {
"total": 233.52762133790208,
"count": 116318,
"self": 8.510360564947973,
"children": {
"TorchPolicy.evaluate": {
"total": 225.0172607729541,
"count": 113419,
"self": 225.0172607729541
}
}
},
"workers": {
"total": 1.5560284590350193,
"count": 116318,
"self": 0.0,
"children": {
"worker_root": {
"total": 4053.256295562092,
"count": 116318,
"is_parallel": true,
"self": 1601.200234990009,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056594679999761865,
"count": 1,
"is_parallel": true,
"self": 0.004150975000072776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015084929999034102,
"count": 8,
"is_parallel": true,
"self": 0.0015084929999034102
}
}
},
"UnityEnvironment.step": {
"total": 0.050421885999980987,
"count": 1,
"is_parallel": true,
"self": 0.000634222999906342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004452790000186724,
"count": 1,
"is_parallel": true,
"self": 0.0004452790000186724
},
"communicator.exchange": {
"total": 0.047645586000044204,
"count": 1,
"is_parallel": true,
"self": 0.047645586000044204
},
"steps_from_proto": {
"total": 0.0016967980000117677,
"count": 1,
"is_parallel": true,
"self": 0.00036156999999548134,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013352280000162864,
"count": 8,
"is_parallel": true,
"self": 0.0013352280000162864
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2452.056060572083,
"count": 116317,
"is_parallel": true,
"self": 60.63887488623914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 43.02669800501138,
"count": 116317,
"is_parallel": true,
"self": 43.02669800501138
},
"communicator.exchange": {
"total": 2167.3946952709516,
"count": 116317,
"is_parallel": true,
"self": 2167.3946952709516
},
"steps_from_proto": {
"total": 180.9957924098809,
"count": 116317,
"is_parallel": true,
"self": 37.12974223485975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 143.86605017502114,
"count": 930536,
"is_parallel": true,
"self": 143.86605017502114
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1144.7217215069534,
"count": 116318,
"self": 5.022114229970157,
"children": {
"process_trajectory": {
"total": 238.31076754898316,
"count": 116318,
"self": 237.88740539598365,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4233621529995162,
"count": 3,
"self": 0.4233621529995162
}
}
},
"_update_policy": {
"total": 901.3888397280001,
"count": 835,
"self": 534.9114279339796,
"children": {
"TorchPPOOptimizer.update": {
"total": 366.47741179402055,
"count": 41365,
"self": 366.47741179402055
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3939998098067008e-06,
"count": 1,
"self": 1.3939998098067008e-06
},
"TrainerController._save_models": {
"total": 0.13612271799956943,
"count": 1,
"self": 0.0020453689994610613,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13407734900010837,
"count": 1,
"self": 0.13407734900010837
}
}
}
}
}
}
}