ppo-Huggy / run_logs /timers.json
Akihi91's picture
Huggy
abfa345 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406930923461914,
"min": 1.406930923461914,
"max": 1.4271732568740845,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69873.8203125,
"min": 68613.359375,
"max": 77746.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.71524288107203,
"min": 79.03481012658227,
"max": 423.06722689075633,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48784.0,
"min": 48784.0,
"max": 50345.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49861.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49861.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.470781087875366,
"min": -0.012553537264466286,
"max": 2.470781087875366,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1475.0562744140625,
"min": -1.481317400932312,
"max": 1538.6951904296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9387794860843037,
"min": 1.9322399103035361,
"max": 3.9699500841451876,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2351.4513531923294,
"min": 228.00430941581726,
"max": 2414.1993669867516,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9387794860843037,
"min": 1.9322399103035361,
"max": 3.9699500841451876,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2351.4513531923294,
"min": 228.00430941581726,
"max": 2414.1993669867516,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017066149404531137,
"min": 0.012700685169450783,
"max": 0.019213532288591118,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051198448213593414,
"min": 0.025401370338901566,
"max": 0.05764059686577336,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06024171296093198,
"min": 0.0232124132104218,
"max": 0.06024171296093198,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18072513888279595,
"min": 0.0464248264208436,
"max": 0.18072513888279595,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.588848803749997e-06,
"min": 3.588848803749997e-06,
"max": 0.000295275001575,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.076654641124999e-05,
"min": 1.076654641124999e-05,
"max": 0.0008438524687158501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119624999999999,
"min": 0.10119624999999999,
"max": 0.19842500000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30358874999999996,
"min": 0.20752165,
"max": 0.5812841500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.969287499999994e-05,
"min": 6.969287499999994e-05,
"max": 0.0049214075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020907862499999983,
"min": 0.00020907862499999983,
"max": 0.014066079085000002,
"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": "1743325687",
"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": "1743328065"
},
"total": 2377.552253399,
"count": 1,
"self": 0.4344340040001953,
"children": {
"run_training.setup": {
"total": 0.023913385000014387,
"count": 1,
"self": 0.023913385000014387
},
"TrainerController.start_learning": {
"total": 2377.09390601,
"count": 1,
"self": 4.2633357450267795,
"children": {
"TrainerController._reset_env": {
"total": 3.198764256000004,
"count": 1,
"self": 3.198764256000004
},
"TrainerController.advance": {
"total": 2369.521329264973,
"count": 231809,
"self": 4.252242442013085,
"children": {
"env_step": {
"total": 1886.6616006119796,
"count": 231809,
"self": 1476.4707190009603,
"children": {
"SubprocessEnvManager._take_step": {
"total": 407.60409704405515,
"count": 231809,
"self": 15.436540506075062,
"children": {
"TorchPolicy.evaluate": {
"total": 392.1675565379801,
"count": 222872,
"self": 392.1675565379801
}
}
},
"workers": {
"total": 2.58678456696407,
"count": 231809,
"self": 0.0,
"children": {
"worker_root": {
"total": 2369.459538085093,
"count": 231809,
"is_parallel": true,
"self": 1163.9220742681446,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009051990000443766,
"count": 1,
"is_parallel": true,
"self": 0.0002666380000846402,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006385609999597364,
"count": 2,
"is_parallel": true,
"self": 0.0006385609999597364
}
}
},
"UnityEnvironment.step": {
"total": 0.02912978500000918,
"count": 1,
"is_parallel": true,
"self": 0.00026123899999674904,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018984700000146404,
"count": 1,
"is_parallel": true,
"self": 0.00018984700000146404
},
"communicator.exchange": {
"total": 0.02783069700001306,
"count": 1,
"is_parallel": true,
"self": 0.02783069700001306
},
"steps_from_proto": {
"total": 0.0008480019999979049,
"count": 1,
"is_parallel": true,
"self": 0.00018797600000652892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000660025999991376,
"count": 2,
"is_parallel": true,
"self": 0.000660025999991376
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1205.5374638169483,
"count": 231808,
"is_parallel": true,
"self": 35.90553419203661,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.52958691904053,
"count": 231808,
"is_parallel": true,
"self": 78.52958691904053
},
"communicator.exchange": {
"total": 1007.9325162409348,
"count": 231808,
"is_parallel": true,
"self": 1007.9325162409348
},
"steps_from_proto": {
"total": 83.16982646493614,
"count": 231808,
"is_parallel": true,
"self": 28.958278869978926,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.21154759495721,
"count": 463616,
"is_parallel": true,
"self": 54.21154759495721
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 478.60748621098,
"count": 231809,
"self": 6.322646717825023,
"children": {
"process_trajectory": {
"total": 155.16857066915475,
"count": 231809,
"self": 153.89425148815462,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2743191810001235,
"count": 10,
"self": 1.2743191810001235
}
}
},
"_update_policy": {
"total": 317.11626882400026,
"count": 97,
"self": 250.28545481300807,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.83081401099219,
"count": 2910,
"self": 66.83081401099219
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.51999936660286e-07,
"count": 1,
"self": 9.51999936660286e-07
},
"TrainerController._save_models": {
"total": 0.11047579200021573,
"count": 1,
"self": 0.0020253370003047166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10845045499991102,
"count": 1,
"self": 0.10845045499991102
}
}
}
}
}
}
}