ppo-Huggy / run_logs /timers.json
pixeldoggo's picture
Huggy
08bd2cb verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015779495239258,
"min": 1.4015779495239258,
"max": 1.4242058992385864,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70657.75,
"min": 68052.7109375,
"max": 75436.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.51472868217054,
"min": 69.94893617021276,
"max": 438.1304347826087,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49352.0,
"min": 49016.0,
"max": 50385.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49772.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49772.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.487743616104126,
"min": 0.023106208071112633,
"max": 2.533310651779175,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1604.5946044921875,
"min": 2.611001491546631,
"max": 1750.27587890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.794267093026361,
"min": 1.6124435421903576,
"max": 4.131956770377814,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2447.3022750020027,
"min": 182.2061202675104,
"max": 2797.33473354578,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.794267093026361,
"min": 1.6124435421903576,
"max": 4.131956770377814,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2447.3022750020027,
"min": 182.2061202675104,
"max": 2797.33473354578,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016951413142507792,
"min": 0.012902824502331593,
"max": 0.019830065297234495,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05085423942752338,
"min": 0.025805649004663186,
"max": 0.05668125241982125,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0610207865635554,
"min": 0.023304346669465306,
"max": 0.0610207865635554,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1830623596906662,
"min": 0.04660869333893061,
"max": 0.1830623596906662,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.1194486268833324e-06,
"min": 4.1194486268833324e-06,
"max": 0.00029538045153985,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2358345880649997e-05,
"min": 1.2358345880649997e-05,
"max": 0.0008443810685396499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137311666666667,
"min": 0.10137311666666667,
"max": 0.19846015000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30411935,
"min": 0.2078801,
"max": 0.58146035,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.851852166666666e-05,
"min": 7.851852166666666e-05,
"max": 0.004923161485000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023555556499999997,
"min": 0.00023555556499999997,
"max": 0.014074871465,
"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": "1729943168",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729945708"
},
"total": 2539.7111980570003,
"count": 1,
"self": 0.47574996999992436,
"children": {
"run_training.setup": {
"total": 0.09103699400003507,
"count": 1,
"self": 0.09103699400003507
},
"TrainerController.start_learning": {
"total": 2539.144411093,
"count": 1,
"self": 4.427446819044235,
"children": {
"TrainerController._reset_env": {
"total": 5.313147766999975,
"count": 1,
"self": 5.313147766999975
},
"TrainerController.advance": {
"total": 2529.287802393956,
"count": 233435,
"self": 4.777122724846322,
"children": {
"env_step": {
"total": 1983.7858269050428,
"count": 233435,
"self": 1565.1656303080088,
"children": {
"SubprocessEnvManager._take_step": {
"total": 415.8598730970345,
"count": 233435,
"self": 15.74876182008478,
"children": {
"TorchPolicy.evaluate": {
"total": 400.1111112769497,
"count": 223013,
"self": 400.1111112769497
}
}
},
"workers": {
"total": 2.760323499999515,
"count": 233435,
"self": 0.0,
"children": {
"worker_root": {
"total": 2531.8923266390098,
"count": 233435,
"is_parallel": true,
"self": 1254.9901363490626,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008279259999994792,
"count": 1,
"is_parallel": true,
"self": 0.00021567300001379408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006122529999856852,
"count": 2,
"is_parallel": true,
"self": 0.0006122529999856852
}
}
},
"UnityEnvironment.step": {
"total": 0.037900441999966006,
"count": 1,
"is_parallel": true,
"self": 0.0003824880000138364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020148699996980213,
"count": 1,
"is_parallel": true,
"self": 0.00020148699996980213
},
"communicator.exchange": {
"total": 0.03648332299997037,
"count": 1,
"is_parallel": true,
"self": 0.03648332299997037
},
"steps_from_proto": {
"total": 0.0008331440000119983,
"count": 1,
"is_parallel": true,
"self": 0.00020649599997568657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006266480000363117,
"count": 2,
"is_parallel": true,
"self": 0.0006266480000363117
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1276.9021902899472,
"count": 233434,
"is_parallel": true,
"self": 38.516770686029304,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.61470782393815,
"count": 233434,
"is_parallel": true,
"self": 83.61470782393815
},
"communicator.exchange": {
"total": 1064.2779961979463,
"count": 233434,
"is_parallel": true,
"self": 1064.2779961979463
},
"steps_from_proto": {
"total": 90.49271558203338,
"count": 233434,
"is_parallel": true,
"self": 32.481191038196755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.01152454383663,
"count": 466868,
"is_parallel": true,
"self": 58.01152454383663
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 540.7248527640668,
"count": 233435,
"self": 6.496328270132153,
"children": {
"process_trajectory": {
"total": 177.91315107793366,
"count": 233435,
"self": 176.55722451293354,
"children": {
"RLTrainer._checkpoint": {
"total": 1.355926565000118,
"count": 10,
"self": 1.355926565000118
}
}
},
"_update_policy": {
"total": 356.315373416001,
"count": 97,
"self": 288.0526140230046,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.26275939299643,
"count": 2910,
"self": 68.26275939299643
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0710000424296595e-06,
"count": 1,
"self": 1.0710000424296595e-06
},
"TrainerController._save_models": {
"total": 0.11601304199984952,
"count": 1,
"self": 0.004411815999901592,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11160122599994793,
"count": 1,
"self": 0.11160122599994793
}
}
}
}
}
}
}