ppo-Huggy / run_logs /timers.json
HusseinEid's picture
Huggy
8d9ca03 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406416654586792,
"min": 1.406416654586792,
"max": 1.42674720287323,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69420.7265625,
"min": 68736.453125,
"max": 76591.65625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.42414860681114,
"min": 74.06306306306307,
"max": 403.19354838709677,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49370.0,
"min": 48976.0,
"max": 50055.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49907.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49907.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.513820171356201,
"min": 0.028576692566275597,
"max": 2.549682140350342,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1621.4140625,
"min": 3.5149331092834473,
"max": 1650.8961181640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9340913403865905,
"min": 1.8087490537786872,
"max": 4.0339527567417806,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2537.4889145493507,
"min": 222.47613361477852,
"max": 2546.231787800789,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9340913403865905,
"min": 1.8087490537786872,
"max": 4.0339527567417806,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2537.4889145493507,
"min": 222.47613361477852,
"max": 2546.231787800789,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01696762761566788,
"min": 0.014005767527851275,
"max": 0.02022725689901108,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05090288284700364,
"min": 0.02801153505570255,
"max": 0.05575152269630053,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06134889440404045,
"min": 0.02391781158124407,
"max": 0.06321844576547543,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18404668321212134,
"min": 0.04783562316248814,
"max": 0.18404668321212134,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.701198766300002e-06,
"min": 3.701198766300002e-06,
"max": 0.000295304626565125,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1103596298900006e-05,
"min": 1.1103596298900006e-05,
"max": 0.0008442024185991999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012337,
"min": 0.1012337,
"max": 0.19843487500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037011,
"min": 0.20762305000000003,
"max": 0.5814008,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.156163000000006e-05,
"min": 7.156163000000006e-05,
"max": 0.004921900262500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002146848900000002,
"min": 0.0002146848900000002,
"max": 0.01407189992,
"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": "1711207350",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711211221"
},
"total": 3870.7283575809997,
"count": 1,
"self": 0.6097044119997008,
"children": {
"run_training.setup": {
"total": 0.06336800099995799,
"count": 1,
"self": 0.06336800099995799
},
"TrainerController.start_learning": {
"total": 3870.055285168,
"count": 1,
"self": 6.760106636107594,
"children": {
"TrainerController._reset_env": {
"total": 3.0395817340000235,
"count": 1,
"self": 3.0395817340000235
},
"TrainerController.advance": {
"total": 3860.1490033728924,
"count": 233063,
"self": 7.614084231708148,
"children": {
"env_step": {
"total": 2505.5732625110186,
"count": 233063,
"self": 2100.773598939978,
"children": {
"SubprocessEnvManager._take_step": {
"total": 400.1810650260511,
"count": 233063,
"self": 23.70885124814464,
"children": {
"TorchPolicy.evaluate": {
"total": 376.47221377790646,
"count": 222907,
"self": 376.47221377790646
}
}
},
"workers": {
"total": 4.618598544989368,
"count": 233063,
"self": 0.0,
"children": {
"worker_root": {
"total": 3857.8543702949364,
"count": 233063,
"is_parallel": true,
"self": 2191.1010350379174,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001033391000021311,
"count": 1,
"is_parallel": true,
"self": 0.0003021930000386419,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000731197999982669,
"count": 2,
"is_parallel": true,
"self": 0.000731197999982669
}
}
},
"UnityEnvironment.step": {
"total": 0.032598881000012625,
"count": 1,
"is_parallel": true,
"self": 0.0004042879999701654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001604729999939991,
"count": 1,
"is_parallel": true,
"self": 0.0001604729999939991
},
"communicator.exchange": {
"total": 0.03115615600000865,
"count": 1,
"is_parallel": true,
"self": 0.03115615600000865
},
"steps_from_proto": {
"total": 0.0008779640000398103,
"count": 1,
"is_parallel": true,
"self": 0.00024090699997714182,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006370570000626685,
"count": 2,
"is_parallel": true,
"self": 0.0006370570000626685
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1666.753335257019,
"count": 233062,
"is_parallel": true,
"self": 52.32663091110817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.2635532139866,
"count": 233062,
"is_parallel": true,
"self": 81.2635532139866
},
"communicator.exchange": {
"total": 1409.1491531769514,
"count": 233062,
"is_parallel": true,
"self": 1409.1491531769514
},
"steps_from_proto": {
"total": 124.01399795497281,
"count": 233062,
"is_parallel": true,
"self": 40.61395541308639,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.40004254188642,
"count": 466124,
"is_parallel": true,
"self": 83.40004254188642
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1346.9616566301656,
"count": 233063,
"self": 11.10243512718148,
"children": {
"process_trajectory": {
"total": 216.8111303239835,
"count": 233063,
"self": 215.66624214798316,
"children": {
"RLTrainer._checkpoint": {
"total": 1.144888176000336,
"count": 10,
"self": 1.144888176000336
}
}
},
"_update_policy": {
"total": 1119.0480911790007,
"count": 97,
"self": 295.33991585799436,
"children": {
"TorchPPOOptimizer.update": {
"total": 823.7081753210064,
"count": 2910,
"self": 823.7081753210064
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0390003808424808e-06,
"count": 1,
"self": 1.0390003808424808e-06
},
"TrainerController._save_models": {
"total": 0.10659238599964738,
"count": 1,
"self": 0.0029974660001244047,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10359491999952297,
"count": 1,
"self": 0.10359491999952297
}
}
}
}
}
}
}