ppo-Huggy / run_logs /timers.json
neopolita's picture
Huggy
8ae73bf
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404906988143921,
"min": 1.404906988143921,
"max": 1.4296423196792603,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71516.7890625,
"min": 68611.5,
"max": 77520.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.17558886509636,
"min": 79.27126805778491,
"max": 428.85470085470087,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50051.0,
"min": 48756.0,
"max": 50241.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999699.0,
"min": 49997.0,
"max": 1999699.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999699.0,
"min": 49997.0,
"max": 1999699.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3279836177825928,
"min": 0.10671191662549973,
"max": 2.456146478652954,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1082.5123291015625,
"min": 12.378582000732422,
"max": 1480.0877685546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.512763787597738,
"min": 1.7288321171855103,
"max": 4.048164545980274,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1633.4351612329483,
"min": 200.5445255935192,
"max": 2368.1762593984604,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.512763787597738,
"min": 1.7288321171855103,
"max": 4.048164545980274,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1633.4351612329483,
"min": 200.5445255935192,
"max": 2368.1762593984604,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016539338707419422,
"min": 0.013196109762475317,
"max": 0.020878936115817245,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04961801612225827,
"min": 0.026392219524950633,
"max": 0.061273920590368416,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.041603557351562716,
"min": 0.021061583515256645,
"max": 0.05989288128912449,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12481067205468815,
"min": 0.04212316703051329,
"max": 0.173128375907739,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3339488887166596e-06,
"min": 3.3339488887166596e-06,
"max": 0.00029535577654807494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0001846666149978e-05,
"min": 1.0001846666149978e-05,
"max": 0.0008440923186359001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111128333333334,
"min": 0.10111128333333334,
"max": 0.19845192500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30333385,
"min": 0.20737490000000003,
"max": 0.5813641,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.545303833333324e-05,
"min": 6.545303833333324e-05,
"max": 0.004922751057499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001963591149999997,
"min": 0.0001963591149999997,
"max": 0.014070068590000002,
"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": "1701639332",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701641393"
},
"total": 2061.33864804,
"count": 1,
"self": 0.3219698069997321,
"children": {
"run_training.setup": {
"total": 0.06023318500001551,
"count": 1,
"self": 0.06023318500001551
},
"TrainerController.start_learning": {
"total": 2060.956445048,
"count": 1,
"self": 4.527088188029666,
"children": {
"TrainerController._reset_env": {
"total": 3.0452389209999637,
"count": 1,
"self": 3.0452389209999637
},
"TrainerController.advance": {
"total": 2053.2840294509706,
"count": 232189,
"self": 4.5310564759934095,
"children": {
"env_step": {
"total": 1616.1019721189825,
"count": 232189,
"self": 1298.0917622751213,
"children": {
"SubprocessEnvManager._take_step": {
"total": 315.1597604359158,
"count": 232189,
"self": 16.291960620921145,
"children": {
"TorchPolicy.evaluate": {
"total": 298.86779981499467,
"count": 223068,
"self": 298.86779981499467
}
}
},
"workers": {
"total": 2.850449407945348,
"count": 232189,
"self": 0.0,
"children": {
"worker_root": {
"total": 2053.169381848003,
"count": 232189,
"is_parallel": true,
"self": 1016.2817515670858,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008275520000324832,
"count": 1,
"is_parallel": true,
"self": 0.0002349559999856865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005925960000467967,
"count": 2,
"is_parallel": true,
"self": 0.0005925960000467967
}
}
},
"UnityEnvironment.step": {
"total": 0.021611503000031007,
"count": 1,
"is_parallel": true,
"self": 0.00024376300007133977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017594300004475372,
"count": 1,
"is_parallel": true,
"self": 0.00017594300004475372
},
"communicator.exchange": {
"total": 0.020687717999976485,
"count": 1,
"is_parallel": true,
"self": 0.020687717999976485
},
"steps_from_proto": {
"total": 0.0005040789999384288,
"count": 1,
"is_parallel": true,
"self": 0.00015348499994161102,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00035059399999681773,
"count": 2,
"is_parallel": true,
"self": 0.00035059399999681773
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1036.8876302809172,
"count": 232188,
"is_parallel": true,
"self": 30.03706621494746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 54.692682895029975,
"count": 232188,
"is_parallel": true,
"self": 54.692682895029975
},
"communicator.exchange": {
"total": 885.5734471119812,
"count": 232188,
"is_parallel": true,
"self": 885.5734471119812
},
"steps_from_proto": {
"total": 66.58443405895855,
"count": 232188,
"is_parallel": true,
"self": 24.691606223796725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.892827835161825,
"count": 464376,
"is_parallel": true,
"self": 41.892827835161825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 432.65100085599477,
"count": 232189,
"self": 6.729315013078576,
"children": {
"process_trajectory": {
"total": 146.21804672791507,
"count": 232189,
"self": 145.18607635391493,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0319703740001387,
"count": 10,
"self": 1.0319703740001387
}
}
},
"_update_policy": {
"total": 279.7036391150011,
"count": 97,
"self": 233.04985721599633,
"children": {
"TorchPPOOptimizer.update": {
"total": 46.6537818990048,
"count": 2910,
"self": 46.6537818990048
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.980000529845711e-07,
"count": 1,
"self": 8.980000529845711e-07
},
"TrainerController._save_models": {
"total": 0.10008758999993006,
"count": 1,
"self": 0.0015600950000589364,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09852749499987112,
"count": 1,
"self": 0.09852749499987112
}
}
}
}
}
}
}