ppo-Huggy / run_logs /timers.json
bee-eater78's picture
Huggy
901de88 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4047253131866455,
"min": 1.4047253131866455,
"max": 1.4255269765853882,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69529.6875,
"min": 68420.375,
"max": 76610.6484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.31902985074628,
"min": 77.97318611987382,
"max": 383.96923076923076,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49483.0,
"min": 49212.0,
"max": 49916.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49878.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49878.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.456178665161133,
"min": 0.029710721224546432,
"max": 2.518244743347168,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1316.51171875,
"min": 3.8326830863952637,
"max": 1537.540283203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.79571527798674,
"min": 1.779842687207599,
"max": 4.067236821577899,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2034.5033890008926,
"min": 229.59970664978027,
"max": 2402.4030641913414,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.79571527798674,
"min": 1.779842687207599,
"max": 4.067236821577899,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2034.5033890008926,
"min": 229.59970664978027,
"max": 2402.4030641913414,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01946013268655709,
"min": 0.012496363708851278,
"max": 0.019979823434065715,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.058380398059671275,
"min": 0.02745145626443749,
"max": 0.058380398059671275,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05207058899104595,
"min": 0.022561701418211063,
"max": 0.06052756735848056,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15621176697313785,
"min": 0.045123402836422126,
"max": 0.1815827020754417,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4751988416333423e-06,
"min": 3.4751988416333423e-06,
"max": 0.0002953195515601499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0425596524900027e-05,
"min": 1.0425596524900027e-05,
"max": 0.0008438709187096999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115836666666671,
"min": 0.10115836666666671,
"max": 0.19843985000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034751000000001,
"min": 0.20744650000000003,
"max": 0.5812903,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.780249666666683e-05,
"min": 6.780249666666683e-05,
"max": 0.0049221485149999996,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002034074900000005,
"min": 0.0002034074900000005,
"max": 0.014066385969999998,
"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": "1720198673",
"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": "1720201235"
},
"total": 2561.150690764,
"count": 1,
"self": 0.7999243119998027,
"children": {
"run_training.setup": {
"total": 0.057515625000064574,
"count": 1,
"self": 0.057515625000064574
},
"TrainerController.start_learning": {
"total": 2560.293250827,
"count": 1,
"self": 4.7066886429888655,
"children": {
"TrainerController._reset_env": {
"total": 2.9852219059999925,
"count": 1,
"self": 2.9852219059999925
},
"TrainerController.advance": {
"total": 2552.4223919140113,
"count": 232632,
"self": 5.178891251034656,
"children": {
"env_step": {
"total": 2018.9357872419994,
"count": 232632,
"self": 1664.4815477349653,
"children": {
"SubprocessEnvManager._take_step": {
"total": 351.3967688760448,
"count": 232632,
"self": 17.8270167831015,
"children": {
"TorchPolicy.evaluate": {
"total": 333.5697520929433,
"count": 222954,
"self": 333.5697520929433
}
}
},
"workers": {
"total": 3.057470630989428,
"count": 232632,
"self": 0.0,
"children": {
"worker_root": {
"total": 2552.5945802099586,
"count": 232632,
"is_parallel": true,
"self": 1213.9331318570207,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009712840000020151,
"count": 1,
"is_parallel": true,
"self": 0.00021359899994877196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007576850000532431,
"count": 2,
"is_parallel": true,
"self": 0.0007576850000532431
}
}
},
"UnityEnvironment.step": {
"total": 0.03028083100002732,
"count": 1,
"is_parallel": true,
"self": 0.0003852500000220971,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020198100003199215,
"count": 1,
"is_parallel": true,
"self": 0.00020198100003199215
},
"communicator.exchange": {
"total": 0.02890772000000652,
"count": 1,
"is_parallel": true,
"self": 0.02890772000000652
},
"steps_from_proto": {
"total": 0.0007858799999667099,
"count": 1,
"is_parallel": true,
"self": 0.00022235399990222504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005635260000644848,
"count": 2,
"is_parallel": true,
"self": 0.0005635260000644848
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1338.661448352938,
"count": 232631,
"is_parallel": true,
"self": 40.98802764990796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.93132553713122,
"count": 232631,
"is_parallel": true,
"self": 87.93132553713122
},
"communicator.exchange": {
"total": 1113.969552038906,
"count": 232631,
"is_parallel": true,
"self": 1113.969552038906
},
"steps_from_proto": {
"total": 95.7725431269929,
"count": 232631,
"is_parallel": true,
"self": 36.454321549946485,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.318221577046415,
"count": 465262,
"is_parallel": true,
"self": 59.318221577046415
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.3077134209772,
"count": 232632,
"self": 7.157584062039518,
"children": {
"process_trajectory": {
"total": 163.4694670609382,
"count": 232632,
"self": 162.1208375629384,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3486294979998092,
"count": 10,
"self": 1.3486294979998092
}
}
},
"_update_policy": {
"total": 357.68066229799945,
"count": 97,
"self": 290.8877338520009,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.79292844599854,
"count": 2910,
"self": 66.79292844599854
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.568999778100988e-06,
"count": 1,
"self": 1.568999778100988e-06
},
"TrainerController._save_models": {
"total": 0.17894679500022903,
"count": 1,
"self": 0.002959395000289078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17598739999993995,
"count": 1,
"self": 0.17598739999993995
}
}
}
}
}
}
}