ppo-Huggy / run_logs /timers.json
raulgadea's picture
Huggy
5ccd872 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408774971961975,
"min": 1.408774971961975,
"max": 1.4291179180145264,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72048.9765625,
"min": 68507.7265625,
"max": 78341.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.20351390922401,
"min": 68.14226519337016,
"max": 375.4736842105263,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49315.0,
"min": 48899.0,
"max": 50217.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49560.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49560.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.50620698928833,
"min": -0.036188896745443344,
"max": 2.5235466957092285,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1711.7393798828125,
"min": -4.7769341468811035,
"max": 1829.5712890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8791350672569664,
"min": 1.7739091136238792,
"max": 4.031855264446243,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2649.449250936508,
"min": 234.15600299835205,
"max": 2917.3188214302063,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8791350672569664,
"min": 1.7739091136238792,
"max": 4.031855264446243,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2649.449250936508,
"min": 234.15600299835205,
"max": 2917.3188214302063,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01669559519117077,
"min": 0.013078886744915509,
"max": 0.019326445318640455,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050086785573512316,
"min": 0.026157773489831018,
"max": 0.05797933595592136,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057302758180432845,
"min": 0.025054432824254035,
"max": 0.06343944426625966,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17190827454129853,
"min": 0.05010886564850807,
"max": 0.18205800304810207,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.114748628449998e-06,
"min": 4.114748628449998e-06,
"max": 0.00029538255153915003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2344245885349993e-05,
"min": 1.2344245885349993e-05,
"max": 0.0008442889685703499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137154999999999,
"min": 0.10137154999999999,
"max": 0.19846085000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30411465,
"min": 0.20787290000000008,
"max": 0.58142965,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.844034499999995e-05,
"min": 7.844034499999995e-05,
"max": 0.004923196415,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023532103499999987,
"min": 0.00023532103499999987,
"max": 0.014073339535000003,
"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": "1714122285",
"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": "1714124751"
},
"total": 2465.680720212,
"count": 1,
"self": 0.44102268799997546,
"children": {
"run_training.setup": {
"total": 0.06336392000002888,
"count": 1,
"self": 0.06336392000002888
},
"TrainerController.start_learning": {
"total": 2465.176333604,
"count": 1,
"self": 4.445817272889599,
"children": {
"TrainerController._reset_env": {
"total": 2.7861938010000813,
"count": 1,
"self": 2.7861938010000813
},
"TrainerController.advance": {
"total": 2457.83568173711,
"count": 233630,
"self": 4.8633299531252305,
"children": {
"env_step": {
"total": 1979.9075233480457,
"count": 233630,
"self": 1643.615718331965,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.2485904570058,
"count": 233630,
"self": 18.082774122933415,
"children": {
"TorchPolicy.evaluate": {
"total": 315.16581633407236,
"count": 223024,
"self": 315.16581633407236
}
}
},
"workers": {
"total": 3.043214559075068,
"count": 233630,
"self": 0.0,
"children": {
"worker_root": {
"total": 2457.693846680919,
"count": 233630,
"is_parallel": true,
"self": 1131.5758710527891,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009105240001190396,
"count": 1,
"is_parallel": true,
"self": 0.00023061200022311823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006799119998959213,
"count": 2,
"is_parallel": true,
"self": 0.0006799119998959213
}
}
},
"UnityEnvironment.step": {
"total": 0.04259157100000266,
"count": 1,
"is_parallel": true,
"self": 0.0027088480001111748,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020322099999248167,
"count": 1,
"is_parallel": true,
"self": 0.00020322099999248167
},
"communicator.exchange": {
"total": 0.03885151899999073,
"count": 1,
"is_parallel": true,
"self": 0.03885151899999073
},
"steps_from_proto": {
"total": 0.0008279829999082722,
"count": 1,
"is_parallel": true,
"self": 0.00024007299998629605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005879099999219761,
"count": 2,
"is_parallel": true,
"self": 0.0005879099999219761
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1326.1179756281297,
"count": 233629,
"is_parallel": true,
"self": 40.04370102808866,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.88644913701387,
"count": 233629,
"is_parallel": true,
"self": 86.88644913701387
},
"communicator.exchange": {
"total": 1104.3534715690157,
"count": 233629,
"is_parallel": true,
"self": 1104.3534715690157
},
"steps_from_proto": {
"total": 94.83435389401143,
"count": 233629,
"is_parallel": true,
"self": 35.96548872719109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.86886516682034,
"count": 467258,
"is_parallel": true,
"self": 58.86886516682034
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 473.0648284359388,
"count": 233630,
"self": 6.4479376519814195,
"children": {
"process_trajectory": {
"total": 165.65834787895733,
"count": 233630,
"self": 164.18971431995806,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4686335589992723,
"count": 10,
"self": 1.4686335589992723
}
}
},
"_update_policy": {
"total": 300.95854290500006,
"count": 97,
"self": 240.24008467999556,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.7184582250045,
"count": 2910,
"self": 60.7184582250045
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0480002856638748e-06,
"count": 1,
"self": 1.0480002856638748e-06
},
"TrainerController._save_models": {
"total": 0.10863974499989126,
"count": 1,
"self": 0.0018927629998870543,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10674698200000421,
"count": 1,
"self": 0.10674698200000421
}
}
}
}
}
}
}