ppo-Huggy / run_logs /timers.json
quadcoders's picture
Huggy
6c220bc verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408380150794983,
"min": 1.408380150794983,
"max": 1.432126522064209,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69050.0625,
"min": 68378.953125,
"max": 77032.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.38342967244701,
"min": 91.00553505535055,
"max": 399.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49504.0,
"min": 48957.0,
"max": 50673.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49923.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49923.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3544094562530518,
"min": 0.05830204486846924,
"max": 2.439352512359619,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1221.9384765625,
"min": 7.287755489349365,
"max": 1276.419677734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6663707779551746,
"min": 1.780026417016983,
"max": 3.7869158485195604,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1902.8464337587357,
"min": 222.50330212712288,
"max": 1980.5569887757301,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6663707779551746,
"min": 1.780026417016983,
"max": 3.7869158485195604,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1902.8464337587357,
"min": 222.50330212712288,
"max": 1980.5569887757301,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017034675406022062,
"min": 0.013032108455627167,
"max": 0.019501570702414026,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05110402621806619,
"min": 0.026064216911254334,
"max": 0.058374975066302195,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05226520684858163,
"min": 0.022102353163063526,
"max": 0.07187133530775705,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1567956205457449,
"min": 0.04420470632612705,
"max": 0.20888676680624485,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.264298911933338e-06,
"min": 3.264298911933338e-06,
"max": 0.000295289326570225,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.792896735800015e-06,
"min": 9.792896735800015e-06,
"max": 0.0008438787187070999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010880666666667,
"min": 0.1010880666666667,
"max": 0.19842977500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032642000000001,
"min": 0.2073115000000001,
"max": 0.5812929,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.429452666666677e-05,
"min": 6.429452666666677e-05,
"max": 0.004921645772500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019288358000000031,
"min": 0.00019288358000000031,
"max": 0.014066515709999998,
"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": "1750347172",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750349641"
},
"total": 2468.575023297,
"count": 1,
"self": 0.4436240629997883,
"children": {
"run_training.setup": {
"total": 0.03147438000007696,
"count": 1,
"self": 0.03147438000007696
},
"TrainerController.start_learning": {
"total": 2468.099924854,
"count": 1,
"self": 4.3845051450553,
"children": {
"TrainerController._reset_env": {
"total": 3.561216480999974,
"count": 1,
"self": 3.561216480999974
},
"TrainerController.advance": {
"total": 2460.045430425945,
"count": 231170,
"self": 4.5255892286900234,
"children": {
"env_step": {
"total": 1989.5698328230255,
"count": 231170,
"self": 1573.149429204143,
"children": {
"SubprocessEnvManager._take_step": {
"total": 413.70583021600805,
"count": 231170,
"self": 15.731560072019647,
"children": {
"TorchPolicy.evaluate": {
"total": 397.9742701439884,
"count": 222879,
"self": 397.9742701439884
}
}
},
"workers": {
"total": 2.714573402874521,
"count": 231170,
"self": 0.0,
"children": {
"worker_root": {
"total": 2460.84286183003,
"count": 231170,
"is_parallel": true,
"self": 1175.7136899371385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008163219999914872,
"count": 1,
"is_parallel": true,
"self": 0.00023142999987157964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005848920001199076,
"count": 2,
"is_parallel": true,
"self": 0.0005848920001199076
}
}
},
"UnityEnvironment.step": {
"total": 0.03117443500002537,
"count": 1,
"is_parallel": true,
"self": 0.0003150510001432849,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019566799994663597,
"count": 1,
"is_parallel": true,
"self": 0.00019566799994663597
},
"communicator.exchange": {
"total": 0.030018579999932626,
"count": 1,
"is_parallel": true,
"self": 0.030018579999932626
},
"steps_from_proto": {
"total": 0.0006451360000028217,
"count": 1,
"is_parallel": true,
"self": 0.0001762289999760469,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00046890700002677477,
"count": 2,
"is_parallel": true,
"self": 0.00046890700002677477
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1285.1291718928915,
"count": 231169,
"is_parallel": true,
"self": 37.61588609688647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.15496439005415,
"count": 231169,
"is_parallel": true,
"self": 80.15496439005415
},
"communicator.exchange": {
"total": 1080.4598985549726,
"count": 231169,
"is_parallel": true,
"self": 1080.4598985549726
},
"steps_from_proto": {
"total": 86.89842285097825,
"count": 231169,
"is_parallel": true,
"self": 30.155101715881756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.743321135096494,
"count": 462338,
"is_parallel": true,
"self": 56.743321135096494
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 465.9500083742297,
"count": 231170,
"self": 6.884997221183539,
"children": {
"process_trajectory": {
"total": 157.42585342504606,
"count": 231170,
"self": 156.20281915404655,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2230342709995057,
"count": 10,
"self": 1.2230342709995057
}
}
},
"_update_policy": {
"total": 301.6391577280001,
"count": 97,
"self": 237.89185725899006,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.74730046901004,
"count": 2910,
"self": 63.74730046901004
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3290000424603932e-06,
"count": 1,
"self": 1.3290000424603932e-06
},
"TrainerController._save_models": {
"total": 0.10877147299970602,
"count": 1,
"self": 0.0016245109995907114,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10714696200011531,
"count": 1,
"self": 0.10714696200011531
}
}
}
}
}
}
}