ppo-Huggy / run_logs /timers.json
weepingdogel's picture
Huggy
f27dbf5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4000904560089111,
"min": 1.4000904560089111,
"max": 1.4262045621871948,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69455.6875,
"min": 69125.265625,
"max": 76768.8046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.56022944550669,
"min": 87.23456790123457,
"max": 417.07438016528926,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49455.0,
"min": 48857.0,
"max": 50466.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49837.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49837.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.345527172088623,
"min": -0.03218771517276764,
"max": 2.422205686569214,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1226.710693359375,
"min": -3.8625259399414062,
"max": 1354.99609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6246360086802087,
"min": 1.8969663135707377,
"max": 3.902965500890969,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1895.6846325397491,
"min": 227.63595762848854,
"max": 2110.8410179018974,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6246360086802087,
"min": 1.8969663135707377,
"max": 3.902965500890969,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1895.6846325397491,
"min": 227.63595762848854,
"max": 2110.8410179018974,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019094924846124035,
"min": 0.014793468259611272,
"max": 0.021043069238900595,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0572847745383721,
"min": 0.030080323915656966,
"max": 0.06108315486829573,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056143100352750885,
"min": 0.02385393682246407,
"max": 0.057199866324663166,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16842930105825266,
"min": 0.04770787364492814,
"max": 0.1715995989739895,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4368988543999947e-06,
"min": 3.4368988543999947e-06,
"max": 0.000295365526544825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0310696563199984e-05,
"min": 1.0310696563199984e-05,
"max": 0.0008441616186127998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114560000000002,
"min": 0.10114560000000002,
"max": 0.1984551750000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30343680000000006,
"min": 0.20741790000000004,
"max": 0.5813871999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.716543999999993e-05,
"min": 6.716543999999993e-05,
"max": 0.004922913232500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020149631999999982,
"min": 0.00020149631999999982,
"max": 0.014071221279999999,
"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": "1736484262",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736486980"
},
"total": 2717.722267852,
"count": 1,
"self": 0.47612956300054066,
"children": {
"run_training.setup": {
"total": 0.05839655599993421,
"count": 1,
"self": 0.05839655599993421
},
"TrainerController.start_learning": {
"total": 2717.1877417329997,
"count": 1,
"self": 4.795812509038569,
"children": {
"TrainerController._reset_env": {
"total": 6.185528055000077,
"count": 1,
"self": 6.185528055000077
},
"TrainerController.advance": {
"total": 2706.088086675961,
"count": 231797,
"self": 4.958594588019423,
"children": {
"env_step": {
"total": 2130.0361314359407,
"count": 231797,
"self": 1672.0302187628408,
"children": {
"SubprocessEnvManager._take_step": {
"total": 454.76671239801135,
"count": 231797,
"self": 16.9005091460549,
"children": {
"TorchPolicy.evaluate": {
"total": 437.86620325195645,
"count": 222932,
"self": 437.86620325195645
}
}
},
"workers": {
"total": 3.239200275088592,
"count": 231797,
"self": 0.0,
"children": {
"worker_root": {
"total": 2709.4212019229863,
"count": 231797,
"is_parallel": true,
"self": 1351.4304628068817,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001001772999984496,
"count": 1,
"is_parallel": true,
"self": 0.0002751770000486431,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007265959999358529,
"count": 2,
"is_parallel": true,
"self": 0.0007265959999358529
}
}
},
"UnityEnvironment.step": {
"total": 0.032140549000018837,
"count": 1,
"is_parallel": true,
"self": 0.0004299500000115586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020125000003190507,
"count": 1,
"is_parallel": true,
"self": 0.00020125000003190507
},
"communicator.exchange": {
"total": 0.0306696610000472,
"count": 1,
"is_parallel": true,
"self": 0.0306696610000472
},
"steps_from_proto": {
"total": 0.0008396879999281737,
"count": 1,
"is_parallel": true,
"self": 0.00023395999983222282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006057280000959508,
"count": 2,
"is_parallel": true,
"self": 0.0006057280000959508
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1357.9907391161046,
"count": 231796,
"is_parallel": true,
"self": 40.338667696957145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.55204529901721,
"count": 231796,
"is_parallel": true,
"self": 91.55204529901721
},
"communicator.exchange": {
"total": 1128.3461767361046,
"count": 231796,
"is_parallel": true,
"self": 1128.3461767361046
},
"steps_from_proto": {
"total": 97.75384938402556,
"count": 231796,
"is_parallel": true,
"self": 37.017973129049324,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.73587625497623,
"count": 463592,
"is_parallel": true,
"self": 60.73587625497623
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 571.0933606520014,
"count": 231797,
"self": 7.131255536021058,
"children": {
"process_trajectory": {
"total": 181.9990974699823,
"count": 231797,
"self": 180.52116134898176,
"children": {
"RLTrainer._checkpoint": {
"total": 1.477936121000539,
"count": 10,
"self": 1.477936121000539
}
}
},
"_update_policy": {
"total": 381.963007645998,
"count": 97,
"self": 311.8478173660011,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.11519027999691,
"count": 2910,
"self": 70.11519027999691
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.303999852098059e-06,
"count": 1,
"self": 1.303999852098059e-06
},
"TrainerController._save_models": {
"total": 0.11831318899976395,
"count": 1,
"self": 0.0022360259995366505,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1160771630002273,
"count": 1,
"self": 0.1160771630002273
}
}
}
}
}
}
}