ppo-Huggy / run_logs /timers.json
faelwen's picture
Huggy
e0cc7bc verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4017564058303833,
"min": 1.4017564058303833,
"max": 1.42856764793396,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70987.75,
"min": 67897.6953125,
"max": 77315.734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.07072691552062,
"min": 94.88565891472868,
"max": 383.51908396946567,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49409.0,
"min": 48887.0,
"max": 50241.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49811.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49811.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.414137363433838,
"min": 0.08782321959733963,
"max": 2.4492604732513428,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1228.7958984375,
"min": 11.41701889038086,
"max": 1261.369140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6725266033633517,
"min": 1.712187227148276,
"max": 3.848768226495275,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1869.316041111946,
"min": 222.5843395292759,
"max": 1963.5386197566986,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6725266033633517,
"min": 1.712187227148276,
"max": 3.848768226495275,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1869.316041111946,
"min": 222.5843395292759,
"max": 1963.5386197566986,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01676358610711759,
"min": 0.013696410858796701,
"max": 0.018945689649424616,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03352717221423518,
"min": 0.02992419372215712,
"max": 0.05683706894827385,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051427319583793485,
"min": 0.022183763939473366,
"max": 0.06379380517949661,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10285463916758697,
"min": 0.044849814971288045,
"max": 0.180359073728323,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.483448505550009e-06,
"min": 4.483448505550009e-06,
"max": 0.00029524425158525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.966897011100018e-06,
"min": 8.966897011100018e-06,
"max": 0.0008438113687295501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10149445000000004,
"min": 0.10149445000000004,
"max": 0.19841475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20298890000000008,
"min": 0.20298890000000008,
"max": 0.58127045,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.457305500000016e-05,
"min": 8.457305500000016e-05,
"max": 0.004920896025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016914611000000033,
"min": 0.00016914611000000033,
"max": 0.014065395455,
"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": "1741078589",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741081850"
},
"total": 3261.249843379,
"count": 1,
"self": 0.37205935199972373,
"children": {
"run_training.setup": {
"total": 0.021868040000072142,
"count": 1,
"self": 0.021868040000072142
},
"TrainerController.start_learning": {
"total": 3260.855915987,
"count": 1,
"self": 4.437044347000665,
"children": {
"TrainerController._reset_env": {
"total": 4.475516019999986,
"count": 1,
"self": 4.475516019999986
},
"TrainerController.advance": {
"total": 3251.856023363999,
"count": 231546,
"self": 4.316079118167181,
"children": {
"env_step": {
"total": 2621.780411299786,
"count": 231546,
"self": 2225.1839827706517,
"children": {
"SubprocessEnvManager._take_step": {
"total": 393.54651572002126,
"count": 231546,
"self": 19.555101684104102,
"children": {
"TorchPolicy.evaluate": {
"total": 373.99141403591716,
"count": 223061,
"self": 373.99141403591716
}
}
},
"workers": {
"total": 3.0499128091128114,
"count": 231546,
"self": 0.0,
"children": {
"worker_root": {
"total": 3245.91362841294,
"count": 231546,
"is_parallel": true,
"self": 1427.9247463679728,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013704010000310518,
"count": 1,
"is_parallel": true,
"self": 0.00035238800001025083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001018013000020801,
"count": 2,
"is_parallel": true,
"self": 0.001018013000020801
}
}
},
"UnityEnvironment.step": {
"total": 0.02152897199994186,
"count": 1,
"is_parallel": true,
"self": 0.00023387599981106177,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020256699986020976,
"count": 1,
"is_parallel": true,
"self": 0.00020256699986020976
},
"communicator.exchange": {
"total": 0.020647874000133015,
"count": 1,
"is_parallel": true,
"self": 0.020647874000133015
},
"steps_from_proto": {
"total": 0.00044465500013757264,
"count": 1,
"is_parallel": true,
"self": 0.00013208100017436664,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000312573999963206,
"count": 2,
"is_parallel": true,
"self": 0.000312573999963206
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1817.988882044967,
"count": 231545,
"is_parallel": true,
"self": 30.0638127069642,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 52.00678735295514,
"count": 231545,
"is_parallel": true,
"self": 52.00678735295514
},
"communicator.exchange": {
"total": 1662.8987180740266,
"count": 231545,
"is_parallel": true,
"self": 1662.8987180740266
},
"steps_from_proto": {
"total": 73.01956391102112,
"count": 231545,
"is_parallel": true,
"self": 29.068328437875607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 43.951235473145516,
"count": 463090,
"is_parallel": true,
"self": 43.951235473145516
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 625.7595329460462,
"count": 231546,
"self": 7.308042116004117,
"children": {
"process_trajectory": {
"total": 182.67608223004117,
"count": 231546,
"self": 181.77041790104136,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9056643289998192,
"count": 10,
"self": 0.9056643289998192
}
}
},
"_update_policy": {
"total": 435.7754086000009,
"count": 96,
"self": 217.30445235200636,
"children": {
"TorchPPOOptimizer.update": {
"total": 218.47095624799454,
"count": 2880,
"self": 218.47095624799454
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.34000127017498e-07,
"count": 1,
"self": 9.34000127017498e-07
},
"TrainerController._save_models": {
"total": 0.08733132199995453,
"count": 1,
"self": 0.002418435999970825,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0849128859999837,
"count": 1,
"self": 0.0849128859999837
}
}
}
}
}
}
}