ppo-Huggy / run_logs /timers.json
DarylR's picture
Huggy
a2cb8f8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4044760465621948,
"min": 1.4044760465621948,
"max": 1.4260671138763428,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70004.703125,
"min": 68039.1953125,
"max": 76904.8515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.45224171539961,
"min": 87.32978723404256,
"max": 434.7068965517241,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49480.0,
"min": 48981.0,
"max": 50426.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999933.0,
"min": 49826.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999933.0,
"min": 49826.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3626818656921387,
"min": 0.06183045729994774,
"max": 2.4649384021759033,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1212.0557861328125,
"min": 7.11050271987915,
"max": 1329.97900390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6666978892759508,
"min": 1.7805301075396331,
"max": 3.8386357772375095,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1881.0160171985626,
"min": 204.7609623670578,
"max": 2058.5445571541786,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6666978892759508,
"min": 1.7805301075396331,
"max": 3.8386357772375095,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1881.0160171985626,
"min": 204.7609623670578,
"max": 2058.5445571541786,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017098981068799427,
"min": 0.013556784032455957,
"max": 0.02067090782317488,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051296943206398285,
"min": 0.027113568064911914,
"max": 0.05634311197015146,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05831253586543931,
"min": 0.022737605342020593,
"max": 0.05831253586543931,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17493760759631793,
"min": 0.04547521068404119,
"max": 0.17493760759631793,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.0863989712333423e-06,
"min": 3.0863989712333423e-06,
"max": 0.00029537280154239996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.259196913700027e-06,
"min": 9.259196913700027e-06,
"max": 0.0008443240685586499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010287666666667,
"min": 0.1010287666666667,
"max": 0.19845759999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3030863000000001,
"min": 0.20719584999999996,
"max": 0.58144135,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.13354566666668e-05,
"min": 6.13354566666668e-05,
"max": 0.00492303424,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018400637000000038,
"min": 0.00018400637000000038,
"max": 0.014073923365000003,
"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": "1720644934",
"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=Fetch_Huggy --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720647493"
},
"total": 2558.663304169,
"count": 1,
"self": 0.42584968299979664,
"children": {
"run_training.setup": {
"total": 0.05325733099994068,
"count": 1,
"self": 0.05325733099994068
},
"TrainerController.start_learning": {
"total": 2558.184197155,
"count": 1,
"self": 4.721137603031821,
"children": {
"TrainerController._reset_env": {
"total": 2.1528977389998545,
"count": 1,
"self": 2.1528977389998545
},
"TrainerController.advance": {
"total": 2551.1881205979685,
"count": 231561,
"self": 4.870617001826304,
"children": {
"env_step": {
"total": 2023.5306584271882,
"count": 231561,
"self": 1666.3519542909175,
"children": {
"SubprocessEnvManager._take_step": {
"total": 354.1414007601077,
"count": 231561,
"self": 18.69723187100567,
"children": {
"TorchPolicy.evaluate": {
"total": 335.444168889102,
"count": 222905,
"self": 335.444168889102
}
}
},
"workers": {
"total": 3.0373033761629813,
"count": 231561,
"self": 0.0,
"children": {
"worker_root": {
"total": 2550.885479125144,
"count": 231561,
"is_parallel": true,
"self": 1211.432733773039,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009506599999440368,
"count": 1,
"is_parallel": true,
"self": 0.000252375999934884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006982840000091528,
"count": 2,
"is_parallel": true,
"self": 0.0006982840000091528
}
}
},
"UnityEnvironment.step": {
"total": 0.030565362000061214,
"count": 1,
"is_parallel": true,
"self": 0.00048709499992583005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020138400009273028,
"count": 1,
"is_parallel": true,
"self": 0.00020138400009273028
},
"communicator.exchange": {
"total": 0.029098434999923484,
"count": 1,
"is_parallel": true,
"self": 0.029098434999923484
},
"steps_from_proto": {
"total": 0.0007784480001191696,
"count": 1,
"is_parallel": true,
"self": 0.00021197399996708555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000566474000152084,
"count": 2,
"is_parallel": true,
"self": 0.000566474000152084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1339.4527453521048,
"count": 231560,
"is_parallel": true,
"self": 40.24343098618033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.05782142291787,
"count": 231560,
"is_parallel": true,
"self": 87.05782142291787
},
"communicator.exchange": {
"total": 1116.9498775709446,
"count": 231560,
"is_parallel": true,
"self": 1116.9498775709446
},
"steps_from_proto": {
"total": 95.20161537206195,
"count": 231560,
"is_parallel": true,
"self": 35.92793175694783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.27368361511412,
"count": 463120,
"is_parallel": true,
"self": 59.27368361511412
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 522.786845168954,
"count": 231561,
"self": 7.3528358390078665,
"children": {
"process_trajectory": {
"total": 164.3721225269469,
"count": 231561,
"self": 163.02755841194744,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3445641149994572,
"count": 10,
"self": 1.3445641149994572
}
}
},
"_update_policy": {
"total": 351.0618868029992,
"count": 97,
"self": 284.2491977169907,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.8126890860085,
"count": 2910,
"self": 66.8126890860085
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.51999936660286e-07,
"count": 1,
"self": 9.51999936660286e-07
},
"TrainerController._save_models": {
"total": 0.12204026300014448,
"count": 1,
"self": 0.002933889000360068,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11910637399978441,
"count": 1,
"self": 0.11910637399978441
}
}
}
}
}
}
}