ppo-Huggy / run_logs /timers.json
kjamesh's picture
Huggy
4cb6a2f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4051779508590698,
"min": 1.4051748514175415,
"max": 1.4277671575546265,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69282.296875,
"min": 69282.296875,
"max": 78043.34375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.45996860282574,
"min": 72.11111111111111,
"max": 417.702479338843,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49342.0,
"min": 49204.0,
"max": 50542.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999984.0,
"min": 49913.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999984.0,
"min": 49913.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.528791666030884,
"min": 0.09465495496988297,
"max": 2.528791666030884,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1610.84033203125,
"min": 11.35859489440918,
"max": 1690.5987548828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.028126264666463,
"min": 1.784243180602789,
"max": 4.117526200393702,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2565.916430592537,
"min": 214.10918167233467,
"max": 2709.0120583176613,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.028126264666463,
"min": 1.784243180602789,
"max": 4.117526200393702,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2565.916430592537,
"min": 214.10918167233467,
"max": 2709.0120583176613,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019110217737033964,
"min": 0.013148797038290163,
"max": 0.019596145830776852,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.057330653211101895,
"min": 0.026297594076580326,
"max": 0.05804640960535229,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0565885790106323,
"min": 0.02064523914208015,
"max": 0.06139713736871878,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1697657370318969,
"min": 0.0412904782841603,
"max": 0.18240920503934224,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.861598712833327e-06,
"min": 3.861598712833327e-06,
"max": 0.000295373476542175,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1584796138499982e-05,
"min": 1.1584796138499982e-05,
"max": 0.0008441824686058497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128716666666666,
"min": 0.10128716666666666,
"max": 0.19845782499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038615,
"min": 0.20770465000000005,
"max": 0.5813941499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.422961666666661e-05,
"min": 7.422961666666661e-05,
"max": 0.0049230454675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022268884999999982,
"min": 0.00022268884999999982,
"max": 0.014071568085,
"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": "1745552648",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745555048"
},
"total": 2399.609523314,
"count": 1,
"self": 0.4443234399996072,
"children": {
"run_training.setup": {
"total": 0.03145903399990857,
"count": 1,
"self": 0.03145903399990857
},
"TrainerController.start_learning": {
"total": 2399.1337408400004,
"count": 1,
"self": 4.372464778014546,
"children": {
"TrainerController._reset_env": {
"total": 3.7911953549999,
"count": 1,
"self": 3.7911953549999
},
"TrainerController.advance": {
"total": 2390.8681382949867,
"count": 233353,
"self": 4.391724280001654,
"children": {
"env_step": {
"total": 1898.8657785689552,
"count": 233353,
"self": 1491.012266472075,
"children": {
"SubprocessEnvManager._take_step": {
"total": 405.26766508095125,
"count": 233353,
"self": 15.508595387935543,
"children": {
"TorchPolicy.evaluate": {
"total": 389.7590696930157,
"count": 222872,
"self": 389.7590696930157
}
}
},
"workers": {
"total": 2.585847015928948,
"count": 233353,
"self": 0.0,
"children": {
"worker_root": {
"total": 2391.5618794309707,
"count": 233353,
"is_parallel": true,
"self": 1180.0455142037567,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008863919999839709,
"count": 1,
"is_parallel": true,
"self": 0.0002461699999685152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006402220000154557,
"count": 2,
"is_parallel": true,
"self": 0.0006402220000154557
}
}
},
"UnityEnvironment.step": {
"total": 0.03263715599996431,
"count": 1,
"is_parallel": true,
"self": 0.0003350789999103654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.003953295000087564,
"count": 1,
"is_parallel": true,
"self": 0.003953295000087564
},
"communicator.exchange": {
"total": 0.027664536999964184,
"count": 1,
"is_parallel": true,
"self": 0.027664536999964184
},
"steps_from_proto": {
"total": 0.0006842450000021927,
"count": 1,
"is_parallel": true,
"self": 0.00020015500001591136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048408999998628133,
"count": 2,
"is_parallel": true,
"self": 0.00048408999998628133
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1211.516365227214,
"count": 233352,
"is_parallel": true,
"self": 37.62664141925052,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.73996061901096,
"count": 233352,
"is_parallel": true,
"self": 79.73996061901096
},
"communicator.exchange": {
"total": 1007.2982811300457,
"count": 233352,
"is_parallel": true,
"self": 1007.2982811300457
},
"steps_from_proto": {
"total": 86.85148205890698,
"count": 233352,
"is_parallel": true,
"self": 30.270939123780067,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.580542935126914,
"count": 466704,
"is_parallel": true,
"self": 56.580542935126914
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.61063544602985,
"count": 233353,
"self": 6.160833920018604,
"children": {
"process_trajectory": {
"total": 166.13723117501172,
"count": 233353,
"self": 164.81496607001122,
"children": {
"RLTrainer._checkpoint": {
"total": 1.322265105000497,
"count": 10,
"self": 1.322265105000497
}
}
},
"_update_policy": {
"total": 315.3125703509995,
"count": 97,
"self": 250.2128516279979,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.09971872300162,
"count": 2910,
"self": 65.09971872300162
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.72999714576872e-07,
"count": 1,
"self": 9.72999714576872e-07
},
"TrainerController._save_models": {
"total": 0.1019414389998019,
"count": 1,
"self": 0.0015596190000906063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1003818199997113,
"count": 1,
"self": 0.1003818199997113
}
}
}
}
}
}
}