ppo-Huggy / run_logs /timers.json
willco-afk's picture
First push
fb22c9e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100347757339478,
"min": 1.4100347757339478,
"max": 1.4275966882705688,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69862.9921875,
"min": 68454.3359375,
"max": 76970.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 109.12527472527472,
"min": 95.60424710424711,
"max": 393.3307086614173,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49652.0,
"min": 48947.0,
"max": 50187.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999372.0,
"min": 49884.0,
"max": 1999372.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999372.0,
"min": 49884.0,
"max": 1999372.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.324885606765747,
"min": 0.06775204837322235,
"max": 2.3635129928588867,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1057.822998046875,
"min": 8.74001407623291,
"max": 1172.230224609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6424712727358055,
"min": 1.6065858639487924,
"max": 3.833348253312625,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1657.3244290947914,
"min": 207.24957644939423,
"max": 1976.5055423378944,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6424712727358055,
"min": 1.6065858639487924,
"max": 3.833348253312625,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1657.3244290947914,
"min": 207.24957644939423,
"max": 1976.5055423378944,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01693946947481082,
"min": 0.013939231482557565,
"max": 0.020710156522788264,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050818408424432464,
"min": 0.02787846296511513,
"max": 0.0547687007036681,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050392227578494285,
"min": 0.022526897210627797,
"max": 0.05613662563264369,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15117668273548285,
"min": 0.045053794421255594,
"max": 0.16840987689793108,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.277398907566661e-06,
"min": 3.277398907566661e-06,
"max": 0.00029538217653927496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.832196722699982e-06,
"min": 9.832196722699982e-06,
"max": 0.0008442447185850999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109243333333333,
"min": 0.10109243333333333,
"max": 0.19846072499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30327729999999997,
"min": 0.2073408,
"max": 0.5814149,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.451242333333324e-05,
"min": 6.451242333333324e-05,
"max": 0.0049231901775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019353726999999973,
"min": 0.00019353726999999973,
"max": 0.014072603509999998,
"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": "1734850344",
"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": "1734852912"
},
"total": 2567.396991687,
"count": 1,
"self": 0.4382713610002611,
"children": {
"run_training.setup": {
"total": 0.09990949999996701,
"count": 1,
"self": 0.09990949999996701
},
"TrainerController.start_learning": {
"total": 2566.858810826,
"count": 1,
"self": 4.698284750055336,
"children": {
"TrainerController._reset_env": {
"total": 5.310694495999996,
"count": 1,
"self": 5.310694495999996
},
"TrainerController.advance": {
"total": 2556.727437877945,
"count": 231207,
"self": 4.928047834977406,
"children": {
"env_step": {
"total": 2028.3123714909607,
"count": 231207,
"self": 1589.139582002021,
"children": {
"SubprocessEnvManager._take_step": {
"total": 436.26178127396463,
"count": 231207,
"self": 16.226295584926902,
"children": {
"TorchPolicy.evaluate": {
"total": 420.0354856890377,
"count": 222906,
"self": 420.0354856890377
}
}
},
"workers": {
"total": 2.9110082149751406,
"count": 231207,
"self": 0.0,
"children": {
"worker_root": {
"total": 2559.321082001078,
"count": 231207,
"is_parallel": true,
"self": 1267.6078959760443,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010243549999131574,
"count": 1,
"is_parallel": true,
"self": 0.00036063699985788844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006637180000552689,
"count": 2,
"is_parallel": true,
"self": 0.0006637180000552689
}
}
},
"UnityEnvironment.step": {
"total": 0.029928740999935144,
"count": 1,
"is_parallel": true,
"self": 0.0003595160000031683,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002099869999483417,
"count": 1,
"is_parallel": true,
"self": 0.0002099869999483417
},
"communicator.exchange": {
"total": 0.028535832999978084,
"count": 1,
"is_parallel": true,
"self": 0.028535832999978084
},
"steps_from_proto": {
"total": 0.0008234050000055504,
"count": 1,
"is_parallel": true,
"self": 0.0002458559999922727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005775490000132777,
"count": 2,
"is_parallel": true,
"self": 0.0005775490000132777
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1291.7131860250338,
"count": 231206,
"is_parallel": true,
"self": 38.09895622691738,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.05734579606064,
"count": 231206,
"is_parallel": true,
"self": 86.05734579606064
},
"communicator.exchange": {
"total": 1076.5567566050372,
"count": 231206,
"is_parallel": true,
"self": 1076.5567566050372
},
"steps_from_proto": {
"total": 91.00012739701867,
"count": 231206,
"is_parallel": true,
"self": 34.13121905993273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.86890833708594,
"count": 462412,
"is_parallel": true,
"self": 56.86890833708594
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 523.4870185520065,
"count": 231207,
"self": 7.034818429014308,
"children": {
"process_trajectory": {
"total": 169.1730450799921,
"count": 231207,
"self": 167.79792407199147,
"children": {
"RLTrainer._checkpoint": {
"total": 1.375121008000633,
"count": 10,
"self": 1.375121008000633
}
}
},
"_update_policy": {
"total": 347.27915504300006,
"count": 97,
"self": 278.9204149249995,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.35874011800058,
"count": 2910,
"self": 68.35874011800058
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4590000319003593e-06,
"count": 1,
"self": 1.4590000319003593e-06
},
"TrainerController._save_models": {
"total": 0.12239224299992202,
"count": 1,
"self": 0.0020857609997619875,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12030648200016003,
"count": 1,
"self": 0.12030648200016003
}
}
}
}
}
}
}