ppo-Huggy / run_logs /timers.json
reichenbach's picture
Huggy initial commit
ed2e1f4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074143171310425,
"min": 1.4074143171310425,
"max": 1.429132342338562,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69659.96875,
"min": 69054.53125,
"max": 77531.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.05409356725146,
"min": 69.47390691114245,
"max": 378.3712121212121,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49285.0,
"min": 48665.0,
"max": 50053.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49988.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49988.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.453019380569458,
"min": 0.14050136506557465,
"max": 2.495774030685425,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1677.865234375,
"min": 18.40567970275879,
"max": 1736.903076171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8313802805734656,
"min": 1.8242340383638862,
"max": 3.9794108806624053,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2620.6641119122505,
"min": 238.9746590256691,
"max": 2737.8010529875755,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8313802805734656,
"min": 1.8242340383638862,
"max": 3.9794108806624053,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2620.6641119122505,
"min": 238.9746590256691,
"max": 2737.8010529875755,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01726078683253339,
"min": 0.013358794099864705,
"max": 0.0206343340566592,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05178236049760017,
"min": 0.02671758819972941,
"max": 0.0619030021699776,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059608637748493086,
"min": 0.022266575942436855,
"max": 0.06322165299206972,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17882591324547925,
"min": 0.04453315188487371,
"max": 0.18049344470103582,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.845798718099998e-06,
"min": 3.845798718099998e-06,
"max": 0.00029535795154734997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1537396154299992e-05,
"min": 1.1537396154299992e-05,
"max": 0.0008441376186207998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012819,
"min": 0.1012819,
"max": 0.19845265,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038457,
"min": 0.20769085000000004,
"max": 0.5813792000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.396680999999992e-05,
"min": 7.396680999999992e-05,
"max": 0.004922787235,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022190042999999977,
"min": 0.00022190042999999977,
"max": 0.014070822080000002,
"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": "1735477997",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735480878"
},
"total": 2881.84405403,
"count": 1,
"self": 0.4780312389998471,
"children": {
"run_training.setup": {
"total": 0.06960569800003213,
"count": 1,
"self": 0.06960569800003213
},
"TrainerController.start_learning": {
"total": 2881.296417093,
"count": 1,
"self": 5.319740886051022,
"children": {
"TrainerController._reset_env": {
"total": 6.030697981000003,
"count": 1,
"self": 6.030697981000003
},
"TrainerController.advance": {
"total": 2869.8244994079487,
"count": 233186,
"self": 5.4633492751695485,
"children": {
"env_step": {
"total": 2289.3123171318157,
"count": 233186,
"self": 1792.303692372843,
"children": {
"SubprocessEnvManager._take_step": {
"total": 493.5619909889349,
"count": 233186,
"self": 18.153865498932646,
"children": {
"TorchPolicy.evaluate": {
"total": 475.40812549000225,
"count": 222844,
"self": 475.40812549000225
}
}
},
"workers": {
"total": 3.4466337700378062,
"count": 233186,
"self": 0.0,
"children": {
"worker_root": {
"total": 2873.3977251799593,
"count": 233186,
"is_parallel": true,
"self": 1426.323181862964,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012953420000485494,
"count": 1,
"is_parallel": true,
"self": 0.0006160049999834882,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006793370000650611,
"count": 2,
"is_parallel": true,
"self": 0.0006793370000650611
}
}
},
"UnityEnvironment.step": {
"total": 0.05701865700007147,
"count": 1,
"is_parallel": true,
"self": 0.0005020260000492272,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024229999985436734,
"count": 1,
"is_parallel": true,
"self": 0.00024229999985436734
},
"communicator.exchange": {
"total": 0.055360834000111936,
"count": 1,
"is_parallel": true,
"self": 0.055360834000111936
},
"steps_from_proto": {
"total": 0.0009134970000559406,
"count": 1,
"is_parallel": true,
"self": 0.00023220200023388315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006812949998220574,
"count": 2,
"is_parallel": true,
"self": 0.0006812949998220574
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1447.0745433169952,
"count": 233185,
"is_parallel": true,
"self": 42.36961769905997,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 97.59192871003347,
"count": 233185,
"is_parallel": true,
"self": 97.59192871003347
},
"communicator.exchange": {
"total": 1205.3942677929226,
"count": 233185,
"is_parallel": true,
"self": 1205.3942677929226
},
"steps_from_proto": {
"total": 101.71872911497917,
"count": 233185,
"is_parallel": true,
"self": 38.8902960200719,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.82843309490727,
"count": 466370,
"is_parallel": true,
"self": 62.82843309490727
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 575.0488330009634,
"count": 233186,
"self": 7.38377616388243,
"children": {
"process_trajectory": {
"total": 214.8890962280816,
"count": 233186,
"self": 213.28526266708195,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6038335609996466,
"count": 10,
"self": 1.6038335609996466
}
}
},
"_update_policy": {
"total": 352.7759606089994,
"count": 97,
"self": 284.20096185199213,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.57499875700728,
"count": 2910,
"self": 68.57499875700728
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2040000001434237e-06,
"count": 1,
"self": 1.2040000001434237e-06
},
"TrainerController._save_models": {
"total": 0.121477614000014,
"count": 1,
"self": 0.00219558800017694,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11928202599983706,
"count": 1,
"self": 0.11928202599983706
}
}
}
}
}
}
}