ppo-Huggy / run_logs /timers.json
alkzzz's picture
Huggy
b3a2d4c
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4017044305801392,
"min": 1.4017022848129272,
"max": 1.4273980855941772,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68895.171875,
"min": 68895.171875,
"max": 76967.2734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.09407665505226,
"min": 80.11382113821138,
"max": 393.6692913385827,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48844.0,
"min": 48844.0,
"max": 49996.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49614.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49614.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4125759601593018,
"min": 0.07827430218458176,
"max": 2.4760820865631104,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1387.231201171875,
"min": 9.86256217956543,
"max": 1477.570068359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.767537882120713,
"min": 1.9623132147013196,
"max": 3.9428104674586884,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2166.33428221941,
"min": 247.25146505236626,
"max": 2298.9221955537796,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.767537882120713,
"min": 1.9623132147013196,
"max": 3.9428104674586884,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2166.33428221941,
"min": 247.25146505236626,
"max": 2298.9221955537796,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015237852184994455,
"min": 0.013188976024361587,
"max": 0.020235324084448315,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04571355655498337,
"min": 0.02776305535517167,
"max": 0.05766386528072569,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05849097168280019,
"min": 0.022709099234392245,
"max": 0.0595773883163929,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17547291504840057,
"min": 0.04541819846878449,
"max": 0.1787321649491787,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5023488325833406e-06,
"min": 3.5023488325833406e-06,
"max": 0.0002953150515616499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0507046497750021e-05,
"min": 1.0507046497750021e-05,
"max": 0.0008440455186515,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116741666666666,
"min": 0.10116741666666666,
"max": 0.19843834999999999,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350225,
"min": 0.20746385,
"max": 0.5813484999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.82540916666668e-05,
"min": 6.82540916666668e-05,
"max": 0.004922073664999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002047622750000004,
"min": 0.0002047622750000004,
"max": 0.01406929015,
"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": "1694606161",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694608711"
},
"total": 2550.517990025,
"count": 1,
"self": 0.7892415340002117,
"children": {
"run_training.setup": {
"total": 0.04316286300002048,
"count": 1,
"self": 0.04316286300002048
},
"TrainerController.start_learning": {
"total": 2549.685585628,
"count": 1,
"self": 4.790549179039772,
"children": {
"TrainerController._reset_env": {
"total": 4.093380984999953,
"count": 1,
"self": 4.093380984999953
},
"TrainerController.advance": {
"total": 2540.61087906096,
"count": 232087,
"self": 5.037226087911222,
"children": {
"env_step": {
"total": 1972.6594853059728,
"count": 232087,
"self": 1660.9643703328761,
"children": {
"SubprocessEnvManager._take_step": {
"total": 308.4979675621165,
"count": 232087,
"self": 17.662219917189418,
"children": {
"TorchPolicy.evaluate": {
"total": 290.8357476449271,
"count": 222898,
"self": 290.8357476449271
}
}
},
"workers": {
"total": 3.1971474109802784,
"count": 232087,
"self": 0.0,
"children": {
"worker_root": {
"total": 2541.6554669509446,
"count": 232087,
"is_parallel": true,
"self": 1190.5968341079715,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009104289999868342,
"count": 1,
"is_parallel": true,
"self": 0.0002525139999534076,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006579150000334266,
"count": 2,
"is_parallel": true,
"self": 0.0006579150000334266
}
}
},
"UnityEnvironment.step": {
"total": 0.029613617999984854,
"count": 1,
"is_parallel": true,
"self": 0.0003141009998444133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002740480000511525,
"count": 1,
"is_parallel": true,
"self": 0.0002740480000511525
},
"communicator.exchange": {
"total": 0.028274263000071187,
"count": 1,
"is_parallel": true,
"self": 0.028274263000071187
},
"steps_from_proto": {
"total": 0.0007512060000181009,
"count": 1,
"is_parallel": true,
"self": 0.00022554999998192216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005256560000361787,
"count": 2,
"is_parallel": true,
"self": 0.0005256560000361787
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1351.058632842973,
"count": 232086,
"is_parallel": true,
"self": 40.860303026849124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.33668080895347,
"count": 232086,
"is_parallel": true,
"self": 86.33668080895347
},
"communicator.exchange": {
"total": 1121.0863643610455,
"count": 232086,
"is_parallel": true,
"self": 1121.0863643610455
},
"steps_from_proto": {
"total": 102.77528464612487,
"count": 232086,
"is_parallel": true,
"self": 38.64159941922662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.13368522689825,
"count": 464172,
"is_parallel": true,
"self": 64.13368522689825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 562.9141676670762,
"count": 232087,
"self": 7.039456530136363,
"children": {
"process_trajectory": {
"total": 145.97229013293986,
"count": 232087,
"self": 144.447622146939,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5246679860008499,
"count": 10,
"self": 1.5246679860008499
}
}
},
"_update_policy": {
"total": 409.90242100399996,
"count": 97,
"self": 348.76941700100247,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.133004002997495,
"count": 2910,
"self": 61.133004002997495
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7370002751704305e-06,
"count": 1,
"self": 1.7370002751704305e-06
},
"TrainerController._save_models": {
"total": 0.19077466599992476,
"count": 1,
"self": 0.002656227999523253,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1881184380004015,
"count": 1,
"self": 0.1881184380004015
}
}
}
}
}
}
}