ppo-Huggy / run_logs /timers.json
N0de's picture
Huggy
1f0663e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4056785106658936,
"min": 1.4056785106658936,
"max": 1.4288619756698608,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68809.3671875,
"min": 68487.84375,
"max": 77801.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.32642487046633,
"min": 80.63132137030995,
"max": 403.41129032258067,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49404.0,
"min": 49354.0,
"max": 50023.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999955.0,
"min": 49447.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999955.0,
"min": 49447.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.471822738647461,
"min": 0.09441374242305756,
"max": 2.491506814956665,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1431.185302734375,
"min": 11.612890243530273,
"max": 1482.446533203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7946991055740593,
"min": 1.8078243963844407,
"max": 3.9671527431792573,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2197.1307821273804,
"min": 222.36240075528622,
"max": 2360.455882191658,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7946991055740593,
"min": 1.8078243963844407,
"max": 3.9671527431792573,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2197.1307821273804,
"min": 222.36240075528622,
"max": 2360.455882191658,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017322449564623334,
"min": 0.013771704781781104,
"max": 0.020855305446457348,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05196734869387001,
"min": 0.02754340956356221,
"max": 0.05433402198286785,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05895342777172725,
"min": 0.021606808838744957,
"max": 0.06110707018524408,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17686028331518175,
"min": 0.043213617677489914,
"max": 0.17897850548227628,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3484488838833325e-06,
"min": 3.3484488838833325e-06,
"max": 0.000295332976555675,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0045346651649998e-05,
"min": 1.0045346651649998e-05,
"max": 0.0008438500687166499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111611666666666,
"min": 0.10111611666666666,
"max": 0.19844432500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30334835,
"min": 0.20740694999999995,
"max": 0.58128335,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.569422166666667e-05,
"min": 6.569422166666667e-05,
"max": 0.004922371817499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000197082665,
"min": 0.000197082665,
"max": 0.014066039165,
"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": "1711344803",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/home/node/WORK/WORKSPACE/ENVS/miscs/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy.x86_64 --run-id=Huggy",
"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": "1711346238"
},
"total": 1434.894635269011,
"count": 1,
"self": 0.3283874430053402,
"children": {
"run_training.setup": {
"total": 0.01943481800844893,
"count": 1,
"self": 0.01943481800844893
},
"TrainerController.start_learning": {
"total": 1434.5468130079971,
"count": 1,
"self": 3.680055793884094,
"children": {
"TrainerController._reset_env": {
"total": 5.050040786009049,
"count": 1,
"self": 5.050040786009049
},
"TrainerController.advance": {
"total": 1425.7134979911061,
"count": 232392,
"self": 3.515716002031695,
"children": {
"env_step": {
"total": 1109.0173720930034,
"count": 232392,
"self": 850.1136682451324,
"children": {
"SubprocessEnvManager._take_step": {
"total": 256.4919471999892,
"count": 232392,
"self": 11.530987256250228,
"children": {
"TorchPolicy.evaluate": {
"total": 244.960959943739,
"count": 222860,
"self": 244.960959943739
}
}
},
"workers": {
"total": 2.4117566478817025,
"count": 232392,
"self": 0.0,
"children": {
"worker_root": {
"total": 1430.1671842681244,
"count": 232392,
"is_parallel": true,
"self": 767.2785620625655,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0004975780029781163,
"count": 1,
"is_parallel": true,
"self": 0.00013026600936427712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00036731199361383915,
"count": 2,
"is_parallel": true,
"self": 0.00036731199361383915
}
}
},
"UnityEnvironment.step": {
"total": 0.013601246988400817,
"count": 1,
"is_parallel": true,
"self": 0.00012119498569518328,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015432499640155584,
"count": 1,
"is_parallel": true,
"self": 0.00015432499640155584
},
"communicator.exchange": {
"total": 0.013060066004982218,
"count": 1,
"is_parallel": true,
"self": 0.013060066004982218
},
"steps_from_proto": {
"total": 0.00026566100132185966,
"count": 1,
"is_parallel": true,
"self": 7.924300734885037e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0001864179939730093,
"count": 2,
"is_parallel": true,
"self": 0.0001864179939730093
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 662.8886222055589,
"count": 232391,
"is_parallel": true,
"self": 20.8046796580893,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 37.708436134518706,
"count": 232391,
"is_parallel": true,
"self": 37.708436134518706
},
"communicator.exchange": {
"total": 555.8705666201276,
"count": 232391,
"is_parallel": true,
"self": 555.8705666201276
},
"steps_from_proto": {
"total": 48.50493979282328,
"count": 232391,
"is_parallel": true,
"self": 17.79693489233614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.70800490048714,
"count": 464782,
"is_parallel": true,
"self": 30.70800490048714
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 313.18040989607107,
"count": 232392,
"self": 4.96074609241623,
"children": {
"process_trajectory": {
"total": 100.9325403036346,
"count": 232392,
"self": 99.3618238606141,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5707164430205012,
"count": 10,
"self": 1.5707164430205012
}
}
},
"_update_policy": {
"total": 207.28712350002024,
"count": 97,
"self": 170.35749344232318,
"children": {
"TorchPPOOptimizer.update": {
"total": 36.92963005769707,
"count": 2910,
"self": 36.92963005769707
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.059999577701092e-07,
"count": 1,
"self": 6.059999577701092e-07
},
"TrainerController._save_models": {
"total": 0.10321783099789172,
"count": 1,
"self": 0.001072915008990094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10214491598890163,
"count": 1,
"self": 0.10214491598890163
}
}
}
}
}
}
}