ppo-Huggy / run_logs /timers.json
youngqui's picture
Huggy
3a4ebff verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4099897146224976,
"min": 1.4099897146224976,
"max": 1.4282640218734741,
"count": 28
},
"Huggy.Policy.Entropy.sum": {
"value": 69601.3203125,
"min": 68558.015625,
"max": 78585.90625,
"count": 28
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.88865546218487,
"min": 86.56392294220666,
"max": 432.0344827586207,
"count": 28
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49451.0,
"min": 49227.0,
"max": 50116.0,
"count": 28
},
"Huggy.Step.mean": {
"value": 1399992.0,
"min": 49702.0,
"max": 1399992.0,
"count": 28
},
"Huggy.Step.sum": {
"value": 1399992.0,
"min": 49702.0,
"max": 1399992.0,
"count": 28
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3731045722961426,
"min": -0.06032945215702057,
"max": 2.428274393081665,
"count": 28
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1129.5977783203125,
"min": -6.937887191772461,
"max": 1341.105712890625,
"count": 28
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7056798410265386,
"min": 1.9644528679225757,
"max": 4.04948935933797,
"count": 28
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1763.9036043286324,
"min": 225.9120798110962,
"max": 2168.7920486927032,
"count": 28
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7056798410265386,
"min": 1.9644528679225757,
"max": 4.04948935933797,
"count": 28
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1763.9036043286324,
"min": 225.9120798110962,
"max": 2168.7920486927032,
"count": 28
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015408531609136845,
"min": 0.013873725187780413,
"max": 0.01977773148828419,
"count": 28
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03081706321827369,
"min": 0.027747450375560825,
"max": 0.054934718707954744,
"count": 28
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.044873447716236116,
"min": 0.02419902678165171,
"max": 0.05936957057565451,
"count": 28
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08974689543247223,
"min": 0.04924718830734491,
"max": 0.17662601582705975,
"count": 28
},
"Huggy.Policy.LearningRate.mean": {
"value": 9.453089348972499e-05,
"min": 9.453089348972499e-05,
"max": 0.00029534692655102497,
"count": 28
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00018906178697944998,
"min": 0.00018906178697944998,
"max": 0.0008437713187428998,
"count": 28
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.13151027500000004,
"min": 0.13151027500000004,
"max": 0.19844897499999997,
"count": 28
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2630205500000001,
"min": 0.2630205500000001,
"max": 0.5812571,
"count": 28
},
"Huggy.Policy.Beta.mean": {
"value": 0.0015823627225000005,
"min": 0.0015823627225000005,
"max": 0.0049226038525000005,
"count": 28
},
"Huggy.Policy.Beta.sum": {
"value": 0.003164725445000001,
"min": 0.003164725445000001,
"max": 0.014064729289999998,
"count": 28
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 28
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 28
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1767706907",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767708752"
},
"total": 1845.185123133,
"count": 1,
"self": 0.27295364199994765,
"children": {
"run_training.setup": {
"total": 0.027595221999945352,
"count": 1,
"self": 0.027595221999945352
},
"TrainerController.start_learning": {
"total": 1844.884574269,
"count": 1,
"self": 3.1729436000475744,
"children": {
"TrainerController._reset_env": {
"total": 2.9717052139999396,
"count": 1,
"self": 2.9717052139999396
},
"TrainerController.advance": {
"total": 1838.5821617029521,
"count": 166857,
"self": 3.099241550831721,
"children": {
"env_step": {
"total": 1496.6037090160298,
"count": 166857,
"self": 1201.633736454868,
"children": {
"SubprocessEnvManager._take_step": {
"total": 292.9928489430745,
"count": 166857,
"self": 11.025100706010335,
"children": {
"TorchPolicy.evaluate": {
"total": 281.96774823706414,
"count": 160498,
"self": 281.96774823706414
}
}
},
"workers": {
"total": 1.9771236180871483,
"count": 166856,
"self": 0.0,
"children": {
"worker_root": {
"total": 1835.9139069060002,
"count": 166856,
"is_parallel": true,
"self": 862.8343155439751,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000837348999993992,
"count": 1,
"is_parallel": true,
"self": 0.00022568599990790972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006116630000860823,
"count": 2,
"is_parallel": true,
"self": 0.0006116630000860823
}
}
},
"UnityEnvironment.step": {
"total": 0.030647940999983803,
"count": 1,
"is_parallel": true,
"self": 0.0003221609999854991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002311599999984537,
"count": 1,
"is_parallel": true,
"self": 0.0002311599999984537
},
"communicator.exchange": {
"total": 0.02943213300000025,
"count": 1,
"is_parallel": true,
"self": 0.02943213300000025
},
"steps_from_proto": {
"total": 0.0006624869999996008,
"count": 1,
"is_parallel": true,
"self": 0.0001787790000662426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004837079999333582,
"count": 2,
"is_parallel": true,
"self": 0.0004837079999333582
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 973.0795913620251,
"count": 166855,
"is_parallel": true,
"self": 26.931503590037437,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 58.30066363405899,
"count": 166855,
"is_parallel": true,
"self": 58.30066363405899
},
"communicator.exchange": {
"total": 824.4407968089611,
"count": 166855,
"is_parallel": true,
"self": 824.4407968089611
},
"steps_from_proto": {
"total": 63.4066273289676,
"count": 166855,
"is_parallel": true,
"self": 22.143093448033937,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.263533880933664,
"count": 333710,
"is_parallel": true,
"self": 41.263533880933664
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 338.8792111360906,
"count": 166856,
"self": 4.857388559111655,
"children": {
"process_trajectory": {
"total": 108.07416943397823,
"count": 166856,
"self": 107.2351804829774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8389889510008288,
"count": 7,
"self": 0.8389889510008288
}
}
},
"_update_policy": {
"total": 225.9476531430007,
"count": 69,
"self": 179.73195771999747,
"children": {
"TorchPPOOptimizer.update": {
"total": 46.21569542300324,
"count": 2070,
"self": 46.21569542300324
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2530003914434928e-06,
"count": 1,
"self": 1.2530003914434928e-06
},
"TrainerController._save_models": {
"total": 0.1577624990000004,
"count": 1,
"self": 0.0017263999998249346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15603609900017545,
"count": 1,
"self": 0.15603609900017545
}
}
}
}
}
}
}