ppo-Huggy / run_logs /timers.json
vlad-skripniuk's picture
Huggy
b219476 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4083054065704346,
"min": 1.4082975387573242,
"max": 1.4312946796417236,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71891.171875,
"min": 69065.875,
"max": 78383.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 132.48533333333333,
"min": 93.31809523809524,
"max": 392.23622047244095,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49682.0,
"min": 48882.0,
"max": 50132.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49692.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49692.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2884325981140137,
"min": 0.07470211386680603,
"max": 2.3935770988464355,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 858.1622314453125,
"min": 9.487168312072754,
"max": 1200.1502685546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3935895346005758,
"min": 1.871867415825213,
"max": 3.8658987701416563,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1272.596075475216,
"min": 237.72716180980206,
"max": 1953.1144280433655,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3935895346005758,
"min": 1.871867415825213,
"max": 3.8658987701416563,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1272.596075475216,
"min": 237.72716180980206,
"max": 1953.1144280433655,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013771215347514954,
"min": 0.013771215347514954,
"max": 0.02191339344426524,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02754243069502991,
"min": 0.02754243069502991,
"max": 0.05828177020594012,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.040707526014496884,
"min": 0.02228243049855034,
"max": 0.0608671124610636,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08141505202899377,
"min": 0.04456486099710068,
"max": 0.1826013373831908,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.536098488000006e-06,
"min": 4.536098488000006e-06,
"max": 0.000295344376551875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.072196976000012e-06,
"min": 9.072196976000012e-06,
"max": 0.0008440281186572998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10151200000000002,
"min": 0.10151200000000002,
"max": 0.19844812500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20302400000000004,
"min": 0.20302400000000004,
"max": 0.5813427000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.544880000000008e-05,
"min": 8.544880000000008e-05,
"max": 0.0049225614375,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017089760000000016,
"min": 0.00017089760000000016,
"max": 0.014069000729999998,
"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": "1705932769",
"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=Huggy --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705935319"
},
"total": 2550.0344112899993,
"count": 1,
"self": 0.7991783150000629,
"children": {
"run_training.setup": {
"total": 0.06924512299974594,
"count": 1,
"self": 0.06924512299974594
},
"TrainerController.start_learning": {
"total": 2549.1659878519995,
"count": 1,
"self": 4.709802777911136,
"children": {
"TrainerController._reset_env": {
"total": 2.151451226000063,
"count": 1,
"self": 2.151451226000063
},
"TrainerController.advance": {
"total": 2542.115105530089,
"count": 231101,
"self": 5.156987619541724,
"children": {
"env_step": {
"total": 2025.6020353323302,
"count": 231101,
"self": 1680.9826570282994,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.4865340609176,
"count": 231101,
"self": 18.519859044808072,
"children": {
"TorchPolicy.evaluate": {
"total": 322.96667501610955,
"count": 223084,
"self": 322.96667501610955
}
}
},
"workers": {
"total": 3.1328442431131407,
"count": 231101,
"self": 0.0,
"children": {
"worker_root": {
"total": 2541.311650753152,
"count": 231101,
"is_parallel": true,
"self": 1182.058054381987,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006547909997607348,
"count": 1,
"is_parallel": true,
"self": 0.00022583399913855828,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00042895700062217657,
"count": 2,
"is_parallel": true,
"self": 0.00042895700062217657
}
}
},
"UnityEnvironment.step": {
"total": 0.03115808900020056,
"count": 1,
"is_parallel": true,
"self": 0.0002916209996328689,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000224946999878739,
"count": 1,
"is_parallel": true,
"self": 0.000224946999878739
},
"communicator.exchange": {
"total": 0.029929409000033047,
"count": 1,
"is_parallel": true,
"self": 0.029929409000033047
},
"steps_from_proto": {
"total": 0.0007121120006559067,
"count": 1,
"is_parallel": true,
"self": 0.00019298800089018187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005191239997657249,
"count": 2,
"is_parallel": true,
"self": 0.0005191239997657249
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1359.2535963711653,
"count": 231100,
"is_parallel": true,
"self": 42.43224004684271,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.14221763906971,
"count": 231100,
"is_parallel": true,
"self": 90.14221763906971
},
"communicator.exchange": {
"total": 1131.4935879559034,
"count": 231100,
"is_parallel": true,
"self": 1131.4935879559034
},
"steps_from_proto": {
"total": 95.18555072934942,
"count": 231100,
"is_parallel": true,
"self": 35.68769775489909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.497852974450325,
"count": 462200,
"is_parallel": true,
"self": 59.497852974450325
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 511.35608257821696,
"count": 231101,
"self": 7.306191870569819,
"children": {
"process_trajectory": {
"total": 156.86290367864785,
"count": 231101,
"self": 155.4645988816501,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3983047969977633,
"count": 10,
"self": 1.3983047969977633
}
}
},
"_update_policy": {
"total": 347.1869870289993,
"count": 96,
"self": 281.2496622319795,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.93732479701976,
"count": 2880,
"self": 65.93732479701976
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.384999450237956e-06,
"count": 1,
"self": 1.384999450237956e-06
},
"TrainerController._save_models": {
"total": 0.18962693299999955,
"count": 1,
"self": 0.007752032999633229,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18187490000036632,
"count": 1,
"self": 0.18187490000036632
}
}
}
}
}
}
}