ppo-Huggy2 / run_logs /timers.json
SungJinD's picture
Huggy2
241ab50 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4004250764846802,
"min": 1.4004250764846802,
"max": 1.423457145690918,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69078.765625,
"min": 68489.4921875,
"max": 78337.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 121.98029556650246,
"min": 85.17413793103448,
"max": 385.53076923076924,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49524.0,
"min": 48855.0,
"max": 50207.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999458.0,
"min": 49644.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999458.0,
"min": 49644.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3208017349243164,
"min": -0.05714360997080803,
"max": 2.390272378921509,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 942.2454833984375,
"min": -7.371525764465332,
"max": 1356.194091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4489168896170086,
"min": 1.826180490643479,
"max": 3.944630810952051,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1400.2602571845055,
"min": 235.5772832930088,
"max": 2188.6154932379723,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4489168896170086,
"min": 1.826180490643479,
"max": 3.944630810952051,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1400.2602571845055,
"min": 235.5772832930088,
"max": 2188.6154932379723,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01832831919245008,
"min": 0.012342029865734124,
"max": 0.020036638639349905,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05498495757735024,
"min": 0.02468405973146825,
"max": 0.06010991591804971,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03969042493651311,
"min": 0.023157865523050228,
"max": 0.05840198534230391,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11907127480953933,
"min": 0.046315731046100456,
"max": 0.17175816384454567,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6046987984666686e-06,
"min": 3.6046987984666686e-06,
"max": 0.00029534715155095,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0814096395400005e-05,
"min": 1.0814096395400005e-05,
"max": 0.0008442492185836,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120153333333333,
"min": 0.10120153333333333,
"max": 0.19844905000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036046,
"min": 0.2075763,
"max": 0.5814163999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.995651333333338e-05,
"min": 6.995651333333338e-05,
"max": 0.004922607595,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020986954000000013,
"min": 0.00020986954000000013,
"max": 0.01407267836,
"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": "1711544571",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711547187"
},
"total": 2616.0224089989997,
"count": 1,
"self": 0.44145625100009056,
"children": {
"run_training.setup": {
"total": 0.09068714999989425,
"count": 1,
"self": 0.09068714999989425
},
"TrainerController.start_learning": {
"total": 2615.490265598,
"count": 1,
"self": 4.752546061938574,
"children": {
"TrainerController._reset_env": {
"total": 3.3705589669998517,
"count": 1,
"self": 3.3705589669998517
},
"TrainerController.advance": {
"total": 2607.2283555290614,
"count": 231762,
"self": 5.040725898220899,
"children": {
"env_step": {
"total": 2093.8166097018775,
"count": 231762,
"self": 1735.1795695029034,
"children": {
"SubprocessEnvManager._take_step": {
"total": 355.3974209020216,
"count": 231762,
"self": 19.355723697130998,
"children": {
"TorchPolicy.evaluate": {
"total": 336.0416972048906,
"count": 223042,
"self": 336.0416972048906
}
}
},
"workers": {
"total": 3.239619296952469,
"count": 231762,
"self": 0.0,
"children": {
"worker_root": {
"total": 2607.5481207518656,
"count": 231762,
"is_parallel": true,
"self": 1204.3996069908835,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010973819998980616,
"count": 1,
"is_parallel": true,
"self": 0.0002678899998045381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008294920000935235,
"count": 2,
"is_parallel": true,
"self": 0.0008294920000935235
}
}
},
"UnityEnvironment.step": {
"total": 0.03450324300001739,
"count": 1,
"is_parallel": true,
"self": 0.00044344100001580955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023587200007568754,
"count": 1,
"is_parallel": true,
"self": 0.00023587200007568754
},
"communicator.exchange": {
"total": 0.032918964999907985,
"count": 1,
"is_parallel": true,
"self": 0.032918964999907985
},
"steps_from_proto": {
"total": 0.0009049650000179099,
"count": 1,
"is_parallel": true,
"self": 0.0002552640000885731,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006497009999293368,
"count": 2,
"is_parallel": true,
"self": 0.0006497009999293368
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1403.148513760982,
"count": 231761,
"is_parallel": true,
"self": 41.93686959193087,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.35599707494453,
"count": 231761,
"is_parallel": true,
"self": 89.35599707494453
},
"communicator.exchange": {
"total": 1170.9664222110428,
"count": 231761,
"is_parallel": true,
"self": 1170.9664222110428
},
"steps_from_proto": {
"total": 100.88922488306389,
"count": 231761,
"is_parallel": true,
"self": 36.13438800125414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.75483688180975,
"count": 463522,
"is_parallel": true,
"self": 64.75483688180975
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.37101992896305,
"count": 231762,
"self": 7.55618139700573,
"children": {
"process_trajectory": {
"total": 160.37751484495857,
"count": 231762,
"self": 158.67979214695902,
"children": {
"RLTrainer._checkpoint": {
"total": 1.697722697999552,
"count": 10,
"self": 1.697722697999552
}
}
},
"_update_policy": {
"total": 340.43732368699875,
"count": 97,
"self": 273.18031557300696,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.25700811399179,
"count": 2910,
"self": 67.25700811399179
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1120000635855831e-06,
"count": 1,
"self": 1.1120000635855831e-06
},
"TrainerController._save_models": {
"total": 0.13880392800001573,
"count": 1,
"self": 0.002724751000187098,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13607917699982863,
"count": 1,
"self": 0.13607917699982863
}
}
}
}
}
}
}