ppo-Huggy / run_logs /timers.json
JKuang96's picture
Huggy
b36a2d7
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4307379722595215,
"min": 1.4191555976867676,
"max": 1.4316529035568237,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72150.6875,
"min": 68637.4140625,
"max": 77545.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.22520661157024,
"min": 90.58974358974359,
"max": 406.8943089430894,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49477.0,
"min": 49118.0,
"max": 50048.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49425.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49425.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.402097702026367,
"min": 0.04690340533852577,
"max": 2.497239589691162,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1162.615234375,
"min": 5.72221565246582,
"max": 1296.0673828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3514712686873667,
"min": 1.8550863493172849,
"max": 3.8656592536945733,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1622.1120940446854,
"min": 226.32053461670876,
"max": 2014.6442852020264,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3514712686873667,
"min": 1.8550863493172849,
"max": 3.8656592536945733,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1622.1120940446854,
"min": 226.32053461670876,
"max": 2014.6442852020264,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015237549479691853,
"min": 0.011520787572953849,
"max": 0.023905526908735434,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04571264843907556,
"min": 0.023041575145907697,
"max": 0.0717165807262063,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.08483497003714242,
"min": 0.026814121318360168,
"max": 0.11325778712828954,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.2545049101114273,
"min": 0.053866561874747275,
"max": 0.33977336138486863,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4843988385666628e-06,
"min": 3.4843988385666628e-06,
"max": 0.00029531910156029993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0453196515699988e-05,
"min": 1.0453196515699988e-05,
"max": 0.0008442090185970001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116143333333334,
"min": 0.10116143333333334,
"max": 0.1984397,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30348430000000004,
"min": 0.20750045,
"max": 0.5814030000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.795552333333328e-05,
"min": 6.795552333333328e-05,
"max": 0.00492214103,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002038665699999998,
"min": 0.0002038665699999998,
"max": 0.014072009699999999,
"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": "1700895312",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/drive/MyDrive/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700897751"
},
"total": 2438.7298139040004,
"count": 1,
"self": 0.8658774000004996,
"children": {
"run_training.setup": {
"total": 0.07150125699990895,
"count": 1,
"self": 0.07150125699990895
},
"TrainerController.start_learning": {
"total": 2437.792435247,
"count": 1,
"self": 4.905192043045645,
"children": {
"TrainerController._reset_env": {
"total": 5.122554901000058,
"count": 1,
"self": 5.122554901000058
},
"TrainerController.advance": {
"total": 2427.6223113719543,
"count": 231495,
"self": 5.344666947044971,
"children": {
"env_step": {
"total": 2120.5441471689455,
"count": 231495,
"self": 1754.7292969060397,
"children": {
"SubprocessEnvManager._take_step": {
"total": 362.6667676309612,
"count": 231495,
"self": 18.331246463018033,
"children": {
"TorchPolicy.evaluate": {
"total": 344.33552116794317,
"count": 222938,
"self": 344.33552116794317
}
}
},
"workers": {
"total": 3.1480826319445896,
"count": 231495,
"self": 0.0,
"children": {
"worker_root": {
"total": 2429.9584996878443,
"count": 231495,
"is_parallel": true,
"self": 1014.0158954338372,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008287979999295203,
"count": 1,
"is_parallel": true,
"self": 0.00027425700000094366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005545409999285766,
"count": 2,
"is_parallel": true,
"self": 0.0005545409999285766
}
}
},
"UnityEnvironment.step": {
"total": 0.03134384400004819,
"count": 1,
"is_parallel": true,
"self": 0.0003034390001630527,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002172129998143646,
"count": 1,
"is_parallel": true,
"self": 0.0002172129998143646
},
"communicator.exchange": {
"total": 0.030093131000057838,
"count": 1,
"is_parallel": true,
"self": 0.030093131000057838
},
"steps_from_proto": {
"total": 0.0007300610000129382,
"count": 1,
"is_parallel": true,
"self": 0.00020005000010314689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005300109999097913,
"count": 2,
"is_parallel": true,
"self": 0.0005300109999097913
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1415.9426042540072,
"count": 231494,
"is_parallel": true,
"self": 40.85188505324459,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.84032132593211,
"count": 231494,
"is_parallel": true,
"self": 89.84032132593211
},
"communicator.exchange": {
"total": 1192.9949962039757,
"count": 231494,
"is_parallel": true,
"self": 1192.9949962039757
},
"steps_from_proto": {
"total": 92.25540167085478,
"count": 231494,
"is_parallel": true,
"self": 34.2927893508795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.96261231997528,
"count": 462988,
"is_parallel": true,
"self": 57.96261231997528
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 301.7334972559638,
"count": 231495,
"self": 7.006117849893599,
"children": {
"process_trajectory": {
"total": 167.34027526506816,
"count": 231495,
"self": 166.2064627520681,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1338125130000662,
"count": 10,
"self": 1.1338125130000662
}
}
},
"_update_policy": {
"total": 127.38710414100206,
"count": 97,
"self": 106.06525963701256,
"children": {
"TorchPPOOptimizer.update": {
"total": 21.321844503989496,
"count": 970,
"self": 21.321844503989496
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3899998521083035e-06,
"count": 1,
"self": 1.3899998521083035e-06
},
"TrainerController._save_models": {
"total": 0.1423755410000922,
"count": 1,
"self": 0.002830535000157397,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1395450059999348,
"count": 1,
"self": 0.1395450059999348
}
}
}
}
}
}
}