ppo-Huggy / run_logs /timers.json
CrispyJLoHalo's picture
Huggy
cdf3398 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4028218984603882,
"min": 1.4028218984603882,
"max": 1.4274804592132568,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70237.890625,
"min": 68827.84375,
"max": 75815.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.06849315068493,
"min": 67.4068493150685,
"max": 402.26612903225805,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49320.0,
"min": 49207.0,
"max": 50330.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999993.0,
"min": 49338.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999993.0,
"min": 49338.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4497008323669434,
"min": -0.04770975559949875,
"max": 2.5607612133026123,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1609.4534912109375,
"min": -5.868299961090088,
"max": 1821.218994140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.679690935477456,
"min": 1.6512581534017392,
"max": 4.048511819913983,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2417.5569446086884,
"min": 203.10475286841393,
"max": 2881.6712378263474,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.679690935477456,
"min": 1.6512581534017392,
"max": 4.048511819913983,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2417.5569446086884,
"min": 203.10475286841393,
"max": 2881.6712378263474,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017899192810162074,
"min": 0.013513397559290753,
"max": 0.019714898504995897,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05369757843048622,
"min": 0.027026795118581505,
"max": 0.05372138964109277,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05927635899020566,
"min": 0.024069954889516035,
"max": 0.06137380270908277,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17782907697061698,
"min": 0.04813990977903207,
"max": 0.17869788681467375,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.9791986736333355e-06,
"min": 3.9791986736333355e-06,
"max": 0.000295326676557775,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1937596020900007e-05,
"min": 1.1937596020900007e-05,
"max": 0.0008440764186412,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10132636666666668,
"min": 0.10132636666666668,
"max": 0.19844222500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30397910000000006,
"min": 0.20778245000000006,
"max": 0.5813588000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.618569666666671e-05,
"min": 7.618569666666671e-05,
"max": 0.0049222670275,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022855709000000013,
"min": 0.00022855709000000013,
"max": 0.014069804120000001,
"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": "1711113218",
"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": "1711115737"
},
"total": 2519.02713237,
"count": 1,
"self": 0.44811854899990067,
"children": {
"run_training.setup": {
"total": 0.08143422900002406,
"count": 1,
"self": 0.08143422900002406
},
"TrainerController.start_learning": {
"total": 2518.497579592,
"count": 1,
"self": 4.603902436999306,
"children": {
"TrainerController._reset_env": {
"total": 3.200795857000003,
"count": 1,
"self": 3.200795857000003
},
"TrainerController.advance": {
"total": 2510.5803819800008,
"count": 233796,
"self": 4.810640202777449,
"children": {
"env_step": {
"total": 2022.864623667029,
"count": 233796,
"self": 1682.9648266560876,
"children": {
"SubprocessEnvManager._take_step": {
"total": 336.8019467009044,
"count": 233796,
"self": 17.79021120794141,
"children": {
"TorchPolicy.evaluate": {
"total": 319.011735492963,
"count": 222956,
"self": 319.011735492963
}
}
},
"workers": {
"total": 3.0978503100370745,
"count": 233796,
"self": 0.0,
"children": {
"worker_root": {
"total": 2510.9421989430143,
"count": 233796,
"is_parallel": true,
"self": 1153.7767961110999,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009075159999838434,
"count": 1,
"is_parallel": true,
"self": 0.00023186100008842914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006756549998954142,
"count": 2,
"is_parallel": true,
"self": 0.0006756549998954142
}
}
},
"UnityEnvironment.step": {
"total": 0.030220429999985754,
"count": 1,
"is_parallel": true,
"self": 0.0004009079999605092,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021709899999677873,
"count": 1,
"is_parallel": true,
"self": 0.00021709899999677873
},
"communicator.exchange": {
"total": 0.028823051000017585,
"count": 1,
"is_parallel": true,
"self": 0.028823051000017585
},
"steps_from_proto": {
"total": 0.0007793720000108806,
"count": 1,
"is_parallel": true,
"self": 0.00021859799994672358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000560774000064157,
"count": 2,
"is_parallel": true,
"self": 0.000560774000064157
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1357.1654028319144,
"count": 233795,
"is_parallel": true,
"self": 40.74040964405185,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.86137499104666,
"count": 233795,
"is_parallel": true,
"self": 87.86137499104666
},
"communicator.exchange": {
"total": 1131.4232959628905,
"count": 233795,
"is_parallel": true,
"self": 1131.4232959628905
},
"steps_from_proto": {
"total": 97.14032223392553,
"count": 233795,
"is_parallel": true,
"self": 37.00827644201411,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.13204579191142,
"count": 467590,
"is_parallel": true,
"self": 60.13204579191142
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.9051181101943,
"count": 233796,
"self": 6.909592799275288,
"children": {
"process_trajectory": {
"total": 167.74290533091892,
"count": 233796,
"self": 166.41114391791905,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3317614129998674,
"count": 10,
"self": 1.3317614129998674
}
}
},
"_update_policy": {
"total": 308.2526199800001,
"count": 97,
"self": 247.0904603550016,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.16215962499848,
"count": 2910,
"self": 61.16215962499848
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0630001270328648e-06,
"count": 1,
"self": 1.0630001270328648e-06
},
"TrainerController._save_models": {
"total": 0.11249825499999133,
"count": 1,
"self": 0.0019699159997799143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11052833900021142,
"count": 1,
"self": 0.11052833900021142
}
}
}
}
}
}
}