ppo-Dog-agent / run_logs /timers.json
Kaith-jeet123's picture
Huggy
c28e942 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046777486801147,
"min": 1.4046777486801147,
"max": 1.4280035495758057,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71226.9921875,
"min": 68948.328125,
"max": 76103.9765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.74157303370787,
"min": 82.9261744966443,
"max": 384.1145038167939,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49524.0,
"min": 48851.0,
"max": 50319.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49914.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49914.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.417891025543213,
"min": 0.26005077362060547,
"max": 2.47636079788208,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1291.15380859375,
"min": 33.80659866333008,
"max": 1469.488037109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.753484612323818,
"min": 1.9755226204028495,
"max": 4.083518420261087,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2004.3607829809189,
"min": 256.81794065237045,
"max": 2308.882976949215,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.753484612323818,
"min": 1.9755226204028495,
"max": 4.083518420261087,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2004.3607829809189,
"min": 256.81794065237045,
"max": 2308.882976949215,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015159151681129718,
"min": 0.014213822331900397,
"max": 0.02093000338645652,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04547745504338915,
"min": 0.030083075918567674,
"max": 0.05837041701791653,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05242964422537221,
"min": 0.019284473142276208,
"max": 0.0565208318332831,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15728893267611663,
"min": 0.038568946284552416,
"max": 0.1663414780050516,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.830648723149999e-06,
"min": 3.830648723149999e-06,
"max": 0.00029536875154375004,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1491946169449998e-05,
"min": 1.1491946169449998e-05,
"max": 0.0008443234685588498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127684999999999,
"min": 0.10127684999999999,
"max": 0.19845625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30383055,
"min": 0.20776025000000004,
"max": 0.5814411500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.371481499999999e-05,
"min": 7.371481499999999e-05,
"max": 0.004922966875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022114444499999998,
"min": 0.00022114444499999998,
"max": 0.014073913385000001,
"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": "1733670269",
"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",
"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": "1733672657"
},
"total": 2387.474014426,
"count": 1,
"self": 0.4263070299998617,
"children": {
"run_training.setup": {
"total": 0.0602880990002177,
"count": 1,
"self": 0.0602880990002177
},
"TrainerController.start_learning": {
"total": 2386.987419297,
"count": 1,
"self": 4.388147954180113,
"children": {
"TrainerController._reset_env": {
"total": 4.977266723999946,
"count": 1,
"self": 4.977266723999946
},
"TrainerController.advance": {
"total": 2377.5147433278203,
"count": 232794,
"self": 4.6101262547531405,
"children": {
"env_step": {
"total": 1871.5991279530726,
"count": 232794,
"self": 1470.2811789099198,
"children": {
"SubprocessEnvManager._take_step": {
"total": 398.63165795204986,
"count": 232794,
"self": 15.31549709710589,
"children": {
"TorchPolicy.evaluate": {
"total": 383.316160854944,
"count": 223054,
"self": 383.316160854944
}
}
},
"workers": {
"total": 2.6862910911029303,
"count": 232794,
"self": 0.0,
"children": {
"worker_root": {
"total": 2379.97719633599,
"count": 232794,
"is_parallel": true,
"self": 1184.0158119859123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000784015999897747,
"count": 1,
"is_parallel": true,
"self": 0.00021728800015807792,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000566727999739669,
"count": 2,
"is_parallel": true,
"self": 0.000566727999739669
}
}
},
"UnityEnvironment.step": {
"total": 0.05924537999999302,
"count": 1,
"is_parallel": true,
"self": 0.000342519000014363,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018591899993225525,
"count": 1,
"is_parallel": true,
"self": 0.00018591899993225525
},
"communicator.exchange": {
"total": 0.05801827699997375,
"count": 1,
"is_parallel": true,
"self": 0.05801827699997375
},
"steps_from_proto": {
"total": 0.0006986650000726513,
"count": 1,
"is_parallel": true,
"self": 0.00017327600016869837,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005253889999039529,
"count": 2,
"is_parallel": true,
"self": 0.0005253889999039529
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1195.9613843500777,
"count": 232793,
"is_parallel": true,
"self": 37.14280922826515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.2490788359305,
"count": 232793,
"is_parallel": true,
"self": 80.2490788359305
},
"communicator.exchange": {
"total": 991.4437817699413,
"count": 232793,
"is_parallel": true,
"self": 991.4437817699413
},
"steps_from_proto": {
"total": 87.12571451594067,
"count": 232793,
"is_parallel": true,
"self": 31.057133500082273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.0685810158584,
"count": 465586,
"is_parallel": true,
"self": 56.0685810158584
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.3054891199945,
"count": 232794,
"self": 6.394842249035264,
"children": {
"process_trajectory": {
"total": 164.9302798009603,
"count": 232794,
"self": 163.67661085796112,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2536689429991839,
"count": 10,
"self": 1.2536689429991839
}
}
},
"_update_policy": {
"total": 329.9803670699989,
"count": 97,
"self": 264.09940918600705,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.88095788399187,
"count": 2910,
"self": 65.88095788399187
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.520000847056508e-07,
"count": 1,
"self": 8.520000847056508e-07
},
"TrainerController._save_models": {
"total": 0.10726043899967408,
"count": 1,
"self": 0.0020889889997306454,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10517144999994343,
"count": 1,
"self": 0.10517144999994343
}
}
}
}
}
}
}