ppo-Huggy / run_logs /timers.json
AKash97's picture
Huggy
aa68a8d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4067264795303345,
"min": 1.4067264795303345,
"max": 1.4271438121795654,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69443.0546875,
"min": 67978.6953125,
"max": 79332.625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.47128378378379,
"min": 79.43225806451613,
"max": 431.3247863247863,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49415.0,
"min": 48756.0,
"max": 50465.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49930.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49930.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.431245803833008,
"min": 0.052386172115802765,
"max": 2.4433388710021973,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1439.2974853515625,
"min": 6.076796054840088,
"max": 1497.9019775390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7964745666328312,
"min": 2.009015035783422,
"max": 3.907108564940534,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2247.512943446636,
"min": 233.045744150877,
"max": 2339.7538363933563,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7964745666328312,
"min": 2.009015035783422,
"max": 3.907108564940534,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2247.512943446636,
"min": 233.045744150877,
"max": 2339.7538363933563,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01873564549281986,
"min": 0.014278582436963914,
"max": 0.019581317336997018,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.056206936478459577,
"min": 0.02855716487392783,
"max": 0.05874395201099106,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05792329733570417,
"min": 0.021438150542477767,
"max": 0.05792329733570417,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17376989200711251,
"min": 0.042876301084955534,
"max": 0.17376989200711251,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4485488505166686e-06,
"min": 3.4485488505166686e-06,
"max": 0.00029531160156279993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0345646551550005e-05,
"min": 1.0345646551550005e-05,
"max": 0.0008438373187209,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114948333333336,
"min": 0.10114948333333336,
"max": 0.19843719999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034484500000001,
"min": 0.20746000000000006,
"max": 0.5812791000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.73592183333334e-05,
"min": 6.73592183333334e-05,
"max": 0.00492201628,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002020776550000002,
"min": 0.0002020776550000002,
"max": 0.01406582709,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720418605",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1720420930"
},
"total": 2324.655568329,
"count": 1,
"self": 0.5453892719992837,
"children": {
"run_training.setup": {
"total": 0.05813299600004029,
"count": 1,
"self": 0.05813299600004029
},
"TrainerController.start_learning": {
"total": 2324.0520460610005,
"count": 1,
"self": 4.162642094071998,
"children": {
"TrainerController._reset_env": {
"total": 3.153206905999923,
"count": 1,
"self": 3.153206905999923
},
"TrainerController.advance": {
"total": 2316.5620734319286,
"count": 231933,
"self": 4.690207743989504,
"children": {
"env_step": {
"total": 1837.2513899629703,
"count": 231933,
"self": 1514.9652087419083,
"children": {
"SubprocessEnvManager._take_step": {
"total": 319.56895342112625,
"count": 231933,
"self": 15.683235584094973,
"children": {
"TorchPolicy.evaluate": {
"total": 303.8857178370313,
"count": 222848,
"self": 303.8857178370313
}
}
},
"workers": {
"total": 2.7172277999356993,
"count": 231933,
"self": 0.0,
"children": {
"worker_root": {
"total": 2317.087491810913,
"count": 231933,
"is_parallel": true,
"self": 1095.1413751179025,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000924887000110175,
"count": 1,
"is_parallel": true,
"self": 0.00021693300004699267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007079540000631823,
"count": 2,
"is_parallel": true,
"self": 0.0007079540000631823
}
}
},
"UnityEnvironment.step": {
"total": 0.029839022000032855,
"count": 1,
"is_parallel": true,
"self": 0.00038984399998298613,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019171899998582376,
"count": 1,
"is_parallel": true,
"self": 0.00019171899998582376
},
"communicator.exchange": {
"total": 0.028496930000073917,
"count": 1,
"is_parallel": true,
"self": 0.028496930000073917
},
"steps_from_proto": {
"total": 0.0007605289999901288,
"count": 1,
"is_parallel": true,
"self": 0.00020335699969109555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005571720002990332,
"count": 2,
"is_parallel": true,
"self": 0.0005571720002990332
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1221.9461166930105,
"count": 231932,
"is_parallel": true,
"self": 38.582132155972886,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.08972491996428,
"count": 231932,
"is_parallel": true,
"self": 79.08972491996428
},
"communicator.exchange": {
"total": 1016.6579293019886,
"count": 231932,
"is_parallel": true,
"self": 1016.6579293019886
},
"steps_from_proto": {
"total": 87.61633031508472,
"count": 231932,
"is_parallel": true,
"self": 31.000501980017816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.61582833506691,
"count": 463864,
"is_parallel": true,
"self": 56.61582833506691
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.6204757249691,
"count": 231933,
"self": 6.29960066397166,
"children": {
"process_trajectory": {
"total": 149.61928727199802,
"count": 231933,
"self": 148.27252246199805,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3467648099999678,
"count": 10,
"self": 1.3467648099999678
}
}
},
"_update_policy": {
"total": 318.7015877889994,
"count": 97,
"self": 255.74153742400858,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.96005036499082,
"count": 2910,
"self": 62.96005036499082
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2479999895731453e-06,
"count": 1,
"self": 1.2479999895731453e-06
},
"TrainerController._save_models": {
"total": 0.17412238099996102,
"count": 1,
"self": 0.0030136200002743863,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17110876099968664,
"count": 1,
"self": 0.17110876099968664
}
}
}
}
}
}
}