ppo-Huggy / run_logs /timers.json
execbat's picture
Huggy
1590aa3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4047648906707764,
"min": 1.4047648906707764,
"max": 1.42739737033844,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70683.5546875,
"min": 68797.53125,
"max": 76442.515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.77221324717286,
"min": 76.97971918876755,
"max": 424.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49379.0,
"min": 49268.0,
"max": 50091.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999905.0,
"min": 49932.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999905.0,
"min": 49932.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.490906000137329,
"min": 0.1487041562795639,
"max": 2.528351306915283,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1541.870849609375,
"min": 17.398386001586914,
"max": 1566.7332763671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8384329905802677,
"min": 1.833558070863414,
"max": 3.9751325927395222,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2375.9900211691856,
"min": 214.52629429101944,
"max": 2501.0065754055977,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8384329905802677,
"min": 1.833558070863414,
"max": 3.9751325927395222,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2375.9900211691856,
"min": 214.52629429101944,
"max": 2501.0065754055977,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015816595369768847,
"min": 0.01354966842805475,
"max": 0.01891538967077698,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04744978610930654,
"min": 0.028820563742677528,
"max": 0.05521071107893173,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05952015899949603,
"min": 0.02144764003654321,
"max": 0.0629382133897808,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1785604769984881,
"min": 0.04289528007308642,
"max": 0.18881464016934238,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.748898750399997e-06,
"min": 3.748898750399997e-06,
"max": 0.000295339876553375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1246696251199992e-05,
"min": 1.1246696251199992e-05,
"max": 0.0008440150686616502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124960000000001,
"min": 0.10124960000000001,
"max": 0.198446625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30374880000000004,
"min": 0.20766025,
"max": 0.58133835,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.235503999999997e-05,
"min": 7.235503999999997e-05,
"max": 0.0049224865875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002170651199999999,
"min": 0.0002170651199999999,
"max": 0.014068783665000001,
"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": "1719343466",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719346080"
},
"total": 2613.644138703,
"count": 1,
"self": 0.7481144309999763,
"children": {
"run_training.setup": {
"total": 0.05497438999998394,
"count": 1,
"self": 0.05497438999998394
},
"TrainerController.start_learning": {
"total": 2612.841049882,
"count": 1,
"self": 4.78661133599735,
"children": {
"TrainerController._reset_env": {
"total": 3.5711688610000465,
"count": 1,
"self": 3.5711688610000465
},
"TrainerController.advance": {
"total": 2604.3030727340024,
"count": 232843,
"self": 5.144519210028648,
"children": {
"env_step": {
"total": 2066.0270947229974,
"count": 232843,
"self": 1709.534283078092,
"children": {
"SubprocessEnvManager._take_step": {
"total": 353.22091652091694,
"count": 232843,
"self": 18.109266799995567,
"children": {
"TorchPolicy.evaluate": {
"total": 335.1116497209214,
"count": 222964,
"self": 335.1116497209214
}
}
},
"workers": {
"total": 3.2718951239885428,
"count": 232843,
"self": 0.0,
"children": {
"worker_root": {
"total": 2604.9702340470308,
"count": 232843,
"is_parallel": true,
"self": 1232.178882247007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008657649999577188,
"count": 1,
"is_parallel": true,
"self": 0.0002687479999394782,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005970170000182407,
"count": 2,
"is_parallel": true,
"self": 0.0005970170000182407
}
}
},
"UnityEnvironment.step": {
"total": 0.055267233999984455,
"count": 1,
"is_parallel": true,
"self": 0.0003892900000437294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020645299991883803,
"count": 1,
"is_parallel": true,
"self": 0.00020645299991883803
},
"communicator.exchange": {
"total": 0.053890042000034555,
"count": 1,
"is_parallel": true,
"self": 0.053890042000034555
},
"steps_from_proto": {
"total": 0.0007814489999873331,
"count": 1,
"is_parallel": true,
"self": 0.00021765799999684532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005637909999904878,
"count": 2,
"is_parallel": true,
"self": 0.0005637909999904878
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1372.7913518000237,
"count": 232842,
"is_parallel": true,
"self": 41.698939593968134,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.30178287406773,
"count": 232842,
"is_parallel": true,
"self": 88.30178287406773
},
"communicator.exchange": {
"total": 1145.7486190320888,
"count": 232842,
"is_parallel": true,
"self": 1145.7486190320888
},
"steps_from_proto": {
"total": 97.04201029989918,
"count": 232842,
"is_parallel": true,
"self": 36.923411311761924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.11859898813725,
"count": 465684,
"is_parallel": true,
"self": 60.11859898813725
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.1314588009764,
"count": 232843,
"self": 7.434148182970375,
"children": {
"process_trajectory": {
"total": 173.52841294000598,
"count": 232843,
"self": 172.11592571800577,
"children": {
"RLTrainer._checkpoint": {
"total": 1.412487222000209,
"count": 10,
"self": 1.412487222000209
}
}
},
"_update_policy": {
"total": 352.168897678,
"count": 97,
"self": 286.2365209349971,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.93237674300292,
"count": 2910,
"self": 65.93237674300292
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4720003491675016e-06,
"count": 1,
"self": 1.4720003491675016e-06
},
"TrainerController._save_models": {
"total": 0.180195478999849,
"count": 1,
"self": 0.003177473999585345,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17701800500026366,
"count": 1,
"self": 0.17701800500026366
}
}
}
}
}
}
}