ppo-Huggy / run_logs /timers.json
sumitraut7's picture
Huggy
51b9237 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4016205072402954,
"min": 1.4016205072402954,
"max": 1.4258184432983398,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69723.609375,
"min": 67918.6796875,
"max": 76280.2421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.07573149741825,
"min": 73.49255952380952,
"max": 403.0806451612903,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49429.0,
"min": 48921.0,
"max": 50117.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49918.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49918.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4638962745666504,
"min": 0.06416705250740051,
"max": 2.5272223949432373,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1431.523681640625,
"min": 7.892547607421875,
"max": 1650.2762451171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8015084820647247,
"min": 1.8561264203815926,
"max": 4.087930935602158,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2208.676428079605,
"min": 228.30354970693588,
"max": 2616.7444536685944,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8015084820647247,
"min": 1.8561264203815926,
"max": 4.087930935602158,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2208.676428079605,
"min": 228.30354970693588,
"max": 2616.7444536685944,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013743974054523276,
"min": 0.013743974054523276,
"max": 0.0203876959780852,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04123192216356983,
"min": 0.02840877304552123,
"max": 0.05512896725655688,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057540889498260285,
"min": 0.021689672178278364,
"max": 0.06316439416259527,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17262266849478086,
"min": 0.04337934435655673,
"max": 0.18444352423151336,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7467487511166737e-06,
"min": 3.7467487511166737e-06,
"max": 0.0002952995265668249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1240246253350021e-05,
"min": 1.1240246253350021e-05,
"max": 0.0008437656187447998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124888333333336,
"min": 0.10124888333333336,
"max": 0.19843317500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30374665000000006,
"min": 0.20763070000000006,
"max": 0.5812552,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.231927833333347e-05,
"min": 7.231927833333347e-05,
"max": 0.004921815432499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002169578350000004,
"min": 0.0002169578350000004,
"max": 0.014064634479999998,
"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": "1743279102",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743281532"
},
"total": 2430.55208846,
"count": 1,
"self": 0.43686196700036817,
"children": {
"run_training.setup": {
"total": 0.023817891999897256,
"count": 1,
"self": 0.023817891999897256
},
"TrainerController.start_learning": {
"total": 2430.091408601,
"count": 1,
"self": 4.268523225969602,
"children": {
"TrainerController._reset_env": {
"total": 3.0827580840000337,
"count": 1,
"self": 3.0827580840000337
},
"TrainerController.advance": {
"total": 2422.62281425703,
"count": 232899,
"self": 4.329673217108848,
"children": {
"env_step": {
"total": 1912.90836821197,
"count": 232899,
"self": 1505.2308565278197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 405.14588655713715,
"count": 232899,
"self": 15.439926725272699,
"children": {
"TorchPolicy.evaluate": {
"total": 389.70595983186445,
"count": 223009,
"self": 389.70595983186445
}
}
},
"workers": {
"total": 2.531625127013058,
"count": 232899,
"self": 0.0,
"children": {
"worker_root": {
"total": 2422.590812878066,
"count": 232899,
"is_parallel": true,
"self": 1190.5705634028786,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011905840001418255,
"count": 1,
"is_parallel": true,
"self": 0.00039849300037531066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007920909997665149,
"count": 2,
"is_parallel": true,
"self": 0.0007920909997665149
}
}
},
"UnityEnvironment.step": {
"total": 0.04654087599988088,
"count": 1,
"is_parallel": true,
"self": 0.00030413500007853145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021251299995128647,
"count": 1,
"is_parallel": true,
"self": 0.00021251299995128647
},
"communicator.exchange": {
"total": 0.04535658199984027,
"count": 1,
"is_parallel": true,
"self": 0.04535658199984027
},
"steps_from_proto": {
"total": 0.0006676460000107909,
"count": 1,
"is_parallel": true,
"self": 0.0001619730001038988,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005056729999068921,
"count": 2,
"is_parallel": true,
"self": 0.0005056729999068921
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1232.0202494751875,
"count": 232898,
"is_parallel": true,
"self": 37.19008064896843,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.1247489430491,
"count": 232898,
"is_parallel": true,
"self": 81.1247489430491
},
"communicator.exchange": {
"total": 1025.9528814860735,
"count": 232898,
"is_parallel": true,
"self": 1025.9528814860735
},
"steps_from_proto": {
"total": 87.75253839709649,
"count": 232898,
"is_parallel": true,
"self": 32.419556337476706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.33298205961978,
"count": 465796,
"is_parallel": true,
"self": 55.33298205961978
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.3847728279511,
"count": 232899,
"self": 6.154961205767222,
"children": {
"process_trajectory": {
"total": 160.52578688118524,
"count": 232899,
"self": 159.2590830361844,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2667038450008477,
"count": 10,
"self": 1.2667038450008477
}
}
},
"_update_policy": {
"total": 338.70402474099865,
"count": 97,
"self": 273.06710241499127,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.63692232600738,
"count": 2910,
"self": 65.63692232600738
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.150000212481245e-07,
"count": 1,
"self": 8.150000212481245e-07
},
"TrainerController._save_models": {
"total": 0.11731221900026867,
"count": 1,
"self": 0.0017801760004658718,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1155320429998028,
"count": 1,
"self": 0.1155320429998028
}
}
}
}
}
}
}