ppo-Huggy / run_logs /timers.json
tinnawit's picture
Huggy
b875ec9 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4095638990402222,
"min": 1.4095638990402222,
"max": 1.4322826862335205,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70664.2578125,
"min": 69068.90625,
"max": 77739.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.38755020080322,
"min": 85.26086956521739,
"max": 420.8067226890756,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49495.0,
"min": 48843.0,
"max": 50133.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999929.0,
"min": 49827.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999929.0,
"min": 49827.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.361046314239502,
"min": 0.0986909568309784,
"max": 2.4244842529296875,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1175.801025390625,
"min": 11.645532608032227,
"max": 1349.2640380859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.552522529918985,
"min": 1.7023195268239004,
"max": 3.9291467287863395,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1769.1562198996544,
"min": 200.87370416522026,
"max": 2125.065742969513,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.552522529918985,
"min": 1.7023195268239004,
"max": 3.9291467287863395,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1769.1562198996544,
"min": 200.87370416522026,
"max": 2125.065742969513,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014875598815463792,
"min": 0.013604683047742584,
"max": 0.01963935389406591,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04462679644639138,
"min": 0.027209366095485167,
"max": 0.058328262401240255,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051197566340367005,
"min": 0.020731271679202717,
"max": 0.06486061594138542,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.153592699021101,
"min": 0.041462543358405435,
"max": 0.19051441674431166,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.350998883033335e-06,
"min": 3.350998883033335e-06,
"max": 0.0002952867015710999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0052996649100005e-05,
"min": 1.0052996649100005e-05,
"max": 0.0008439024186992,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111696666666666,
"min": 0.10111696666666666,
"max": 0.19842889999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033509,
"min": 0.20736040000000006,
"max": 0.5813008,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.573663666666672e-05,
"min": 6.573663666666672e-05,
"max": 0.004921602110000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019720991000000013,
"min": 0.00019720991000000013,
"max": 0.014066909919999999,
"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": "1712369634",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712372312"
},
"total": 2677.6778570779998,
"count": 1,
"self": 0.4876025549992846,
"children": {
"run_training.setup": {
"total": 0.05869556200002535,
"count": 1,
"self": 0.05869556200002535
},
"TrainerController.start_learning": {
"total": 2677.1315589610003,
"count": 1,
"self": 4.998763403946214,
"children": {
"TrainerController._reset_env": {
"total": 3.039944169000023,
"count": 1,
"self": 3.039944169000023
},
"TrainerController.advance": {
"total": 2668.945159545054,
"count": 231281,
"self": 5.0822812329124645,
"children": {
"env_step": {
"total": 2160.040060736056,
"count": 231281,
"self": 1782.50184002696,
"children": {
"SubprocessEnvManager._take_step": {
"total": 374.12981543999376,
"count": 231281,
"self": 19.069916599021667,
"children": {
"TorchPolicy.evaluate": {
"total": 355.0598988409721,
"count": 222942,
"self": 355.0598988409721
}
}
},
"workers": {
"total": 3.408405269102218,
"count": 231281,
"self": 0.0,
"children": {
"worker_root": {
"total": 2669.1186443309794,
"count": 231281,
"is_parallel": true,
"self": 1235.357706542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010905350000030012,
"count": 1,
"is_parallel": true,
"self": 0.00025590199993530405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008346330000676971,
"count": 2,
"is_parallel": true,
"self": 0.0008346330000676971
}
}
},
"UnityEnvironment.step": {
"total": 0.034942056000090815,
"count": 1,
"is_parallel": true,
"self": 0.00044663200014838367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022711600001912302,
"count": 1,
"is_parallel": true,
"self": 0.00022711600001912302
},
"communicator.exchange": {
"total": 0.03337664899993342,
"count": 1,
"is_parallel": true,
"self": 0.03337664899993342
},
"steps_from_proto": {
"total": 0.0008916589999898861,
"count": 1,
"is_parallel": true,
"self": 0.00025822199995673145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006334370000331546,
"count": 2,
"is_parallel": true,
"self": 0.0006334370000331546
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1433.7609377889794,
"count": 231280,
"is_parallel": true,
"self": 42.54491821687361,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 94.22399046187809,
"count": 231280,
"is_parallel": true,
"self": 94.22399046187809
},
"communicator.exchange": {
"total": 1195.4970503310528,
"count": 231280,
"is_parallel": true,
"self": 1195.4970503310528
},
"steps_from_proto": {
"total": 101.49497877917486,
"count": 231280,
"is_parallel": true,
"self": 37.95164640421092,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.54333237496394,
"count": 462560,
"is_parallel": true,
"self": 63.54333237496394
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.82281757608564,
"count": 231281,
"self": 7.683195301015758,
"children": {
"process_trajectory": {
"total": 169.43305309307118,
"count": 231281,
"self": 167.9757315080716,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4573215849995904,
"count": 10,
"self": 1.4573215849995904
}
}
},
"_update_policy": {
"total": 326.7065691819987,
"count": 97,
"self": 261.71144486598655,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.99512431601215,
"count": 2910,
"self": 64.99512431601215
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1580000318645034e-06,
"count": 1,
"self": 1.1580000318645034e-06
},
"TrainerController._save_models": {
"total": 0.14769068499981586,
"count": 1,
"self": 0.0032089030000861385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14448178199972972,
"count": 1,
"self": 0.14448178199972972
}
}
}
}
}
}
}