ppo-Huggy / run_logs /timers.json
Protao's picture
Huggy
ceb6c9a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3990741968154907,
"min": 1.3990741968154907,
"max": 1.4284849166870117,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68341.9765625,
"min": 68341.9765625,
"max": 75697.2109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.07475083056478,
"min": 69.92989985693849,
"max": 378.1578947368421,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48807.0,
"min": 48807.0,
"max": 50295.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49852.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49852.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.494464635848999,
"min": 0.17591774463653564,
"max": 2.539391279220581,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1501.667724609375,
"min": 23.221141815185547,
"max": 1697.1429443359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8281235752311655,
"min": 1.7804795946135665,
"max": 4.076032019313425,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2304.5303922891617,
"min": 235.02330648899078,
"max": 2686.224784076214,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8281235752311655,
"min": 1.7804795946135665,
"max": 4.076032019313425,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2304.5303922891617,
"min": 235.02330648899078,
"max": 2686.224784076214,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01532802860690228,
"min": 0.013741337354036256,
"max": 0.019403071765070005,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045984085820706844,
"min": 0.028953739013134812,
"max": 0.05611411011074476,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05792207593719165,
"min": 0.020802974918236336,
"max": 0.059692194064458214,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17376622781157494,
"min": 0.04160594983647267,
"max": 0.17429522847135862,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.887598704166666e-06,
"min": 3.887598704166666e-06,
"max": 0.00029530800156399995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1662796112499997e-05,
"min": 1.1662796112499997e-05,
"max": 0.0008440408686530499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129583333333332,
"min": 0.10129583333333332,
"max": 0.19843599999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038875,
"min": 0.20772515000000008,
"max": 0.5813469499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.466208333333333e-05,
"min": 7.466208333333333e-05,
"max": 0.0049219564,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022398625,
"min": 0.00022398625,
"max": 0.014069212804999997,
"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": "1701615075",
"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": "1701617753"
},
"total": 2677.951563901,
"count": 1,
"self": 0.49801211800013334,
"children": {
"run_training.setup": {
"total": 0.0595223980000128,
"count": 1,
"self": 0.0595223980000128
},
"TrainerController.start_learning": {
"total": 2677.394029385,
"count": 1,
"self": 5.222726356904332,
"children": {
"TrainerController._reset_env": {
"total": 4.341164861000038,
"count": 1,
"self": 4.341164861000038
},
"TrainerController.advance": {
"total": 2667.724325498096,
"count": 233831,
"self": 5.330224368020026,
"children": {
"env_step": {
"total": 2110.5460944820024,
"count": 233831,
"self": 1748.2836491210264,
"children": {
"SubprocessEnvManager._take_step": {
"total": 358.83569708000925,
"count": 233831,
"self": 18.286307874836098,
"children": {
"TorchPolicy.evaluate": {
"total": 340.54938920517316,
"count": 222952,
"self": 340.54938920517316
}
}
},
"workers": {
"total": 3.4267482809668763,
"count": 233831,
"self": 0.0,
"children": {
"worker_root": {
"total": 2669.521529144893,
"count": 233831,
"is_parallel": true,
"self": 1253.8074263859662,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009407549999878029,
"count": 1,
"is_parallel": true,
"self": 0.00028996600008213136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006507889999056715,
"count": 2,
"is_parallel": true,
"self": 0.0006507889999056715
}
}
},
"UnityEnvironment.step": {
"total": 0.05290973700004997,
"count": 1,
"is_parallel": true,
"self": 0.00034580100009407033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021550600001774,
"count": 1,
"is_parallel": true,
"self": 0.00021550600001774
},
"communicator.exchange": {
"total": 0.05156411099994784,
"count": 1,
"is_parallel": true,
"self": 0.05156411099994784
},
"steps_from_proto": {
"total": 0.0007843189999903188,
"count": 1,
"is_parallel": true,
"self": 0.00021640800002842298,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005679109999618959,
"count": 2,
"is_parallel": true,
"self": 0.0005679109999618959
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1415.7141027589269,
"count": 233830,
"is_parallel": true,
"self": 42.13067930897637,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.0360084240017,
"count": 233830,
"is_parallel": true,
"self": 93.0360084240017
},
"communicator.exchange": {
"total": 1181.856371670029,
"count": 233830,
"is_parallel": true,
"self": 1181.856371670029
},
"steps_from_proto": {
"total": 98.69104335591987,
"count": 233830,
"is_parallel": true,
"self": 36.95308720675882,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.73795614916105,
"count": 467660,
"is_parallel": true,
"self": 61.73795614916105
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 551.8480066480734,
"count": 233831,
"self": 7.68977280210504,
"children": {
"process_trajectory": {
"total": 179.01703137596814,
"count": 233831,
"self": 177.74333371696787,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2736976590002769,
"count": 10,
"self": 1.2736976590002769
}
}
},
"_update_policy": {
"total": 365.14120247000017,
"count": 97,
"self": 298.52454602399655,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.61665644600362,
"count": 2910,
"self": 66.61665644600362
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.93999947240809e-07,
"count": 1,
"self": 9.93999947240809e-07
},
"TrainerController._save_models": {
"total": 0.10581167500004085,
"count": 1,
"self": 0.0017341170000690909,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10407755799997176,
"count": 1,
"self": 0.10407755799997176
}
}
}
}
}
}
}