ppo-Huggy / run_logs /timers.json
abayuen's picture
Huggy
8315f8c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403585433959961,
"min": 1.403585433959961,
"max": 1.427217960357666,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70744.9140625,
"min": 67875.234375,
"max": 75881.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.8658088235294,
"min": 84.13458262350937,
"max": 396.3968253968254,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49431.0,
"min": 48866.0,
"max": 50131.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999993.0,
"min": 49600.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999993.0,
"min": 49600.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4114644527435303,
"min": -0.00857023149728775,
"max": 2.4446215629577637,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1311.836669921875,
"min": -1.0712789297103882,
"max": 1393.113037109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6940108503708067,
"min": 1.726593663930893,
"max": 3.975848993429771,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2009.541902601719,
"min": 215.82420799136162,
"max": 2189.761006593704,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6940108503708067,
"min": 1.726593663930893,
"max": 3.975848993429771,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2009.541902601719,
"min": 215.82420799136162,
"max": 2189.761006593704,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018945401462648684,
"min": 0.01297006162173299,
"max": 0.0212529233822958,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05683620438794605,
"min": 0.028498624378941413,
"max": 0.06064333155712423,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05149748089412848,
"min": 0.02262893104925752,
"max": 0.06283635254949331,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15449244268238543,
"min": 0.04525786209851504,
"max": 0.185778954004248,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3010988996666644e-06,
"min": 3.3010988996666644e-06,
"max": 0.00029536080154639994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.903296698999994e-06,
"min": 9.903296698999994e-06,
"max": 0.00084424186858605,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110033333333335,
"min": 0.10110033333333335,
"max": 0.19845359999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30330100000000004,
"min": 0.20739205000000005,
"max": 0.5814139500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.490663333333332e-05,
"min": 6.490663333333332e-05,
"max": 0.00492283464,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019471989999999994,
"min": 0.00019471989999999994,
"max": 0.014072556104999998,
"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": "1739823925",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739828219"
},
"total": 4293.402585088,
"count": 1,
"self": 1.109887694000463,
"children": {
"run_training.setup": {
"total": 0.02868032900005346,
"count": 1,
"self": 0.02868032900005346
},
"TrainerController.start_learning": {
"total": 4292.264017064999,
"count": 1,
"self": 8.401201136016425,
"children": {
"TrainerController._reset_env": {
"total": 3.1050437129999864,
"count": 1,
"self": 3.1050437129999864
},
"TrainerController.advance": {
"total": 4280.5460425219835,
"count": 232031,
"self": 8.474173825041362,
"children": {
"env_step": {
"total": 2797.060728126068,
"count": 232031,
"self": 2328.5396024462025,
"children": {
"SubprocessEnvManager._take_step": {
"total": 463.44922926894264,
"count": 232031,
"self": 28.42563826292121,
"children": {
"TorchPolicy.evaluate": {
"total": 435.02359100602143,
"count": 222978,
"self": 435.02359100602143
}
}
},
"workers": {
"total": 5.0718964109230456,
"count": 232031,
"self": 0.0,
"children": {
"worker_root": {
"total": 4279.351758654192,
"count": 232031,
"is_parallel": true,
"self": 2413.613318252087,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014567959999567393,
"count": 1,
"is_parallel": true,
"self": 0.0004922339999211545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009645620000355848,
"count": 2,
"is_parallel": true,
"self": 0.0009645620000355848
}
}
},
"UnityEnvironment.step": {
"total": 0.03567028199995548,
"count": 1,
"is_parallel": true,
"self": 0.00039190199981931073,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021085299999867857,
"count": 1,
"is_parallel": true,
"self": 0.00021085299999867857
},
"communicator.exchange": {
"total": 0.03423528300004364,
"count": 1,
"is_parallel": true,
"self": 0.03423528300004364
},
"steps_from_proto": {
"total": 0.0008322440000938514,
"count": 1,
"is_parallel": true,
"self": 0.00021942700004728977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006128170000465616,
"count": 2,
"is_parallel": true,
"self": 0.0006128170000465616
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1865.738440402105,
"count": 232030,
"is_parallel": true,
"self": 59.26704603325629,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 107.57940043687881,
"count": 232030,
"is_parallel": true,
"self": 107.57940043687881
},
"communicator.exchange": {
"total": 1567.8493875488412,
"count": 232030,
"is_parallel": true,
"self": 1567.8493875488412
},
"steps_from_proto": {
"total": 131.0426063831287,
"count": 232030,
"is_parallel": true,
"self": 42.271763496354424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.77084288677429,
"count": 464060,
"is_parallel": true,
"self": 88.77084288677429
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1475.011140570874,
"count": 232031,
"self": 12.287942423966115,
"children": {
"process_trajectory": {
"total": 242.67384587190804,
"count": 232031,
"self": 241.375408101909,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2984377699990546,
"count": 10,
"self": 1.2984377699990546
}
}
},
"_update_policy": {
"total": 1220.0493522749998,
"count": 97,
"self": 314.15904807701213,
"children": {
"TorchPPOOptimizer.update": {
"total": 905.8903041979877,
"count": 2910,
"self": 905.8903041979877
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2849995982833207e-06,
"count": 1,
"self": 1.2849995982833207e-06
},
"TrainerController._save_models": {
"total": 0.21172840899998846,
"count": 1,
"self": 0.01058818000001338,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20114022899997508,
"count": 1,
"self": 0.20114022899997508
}
}
}
}
}
}
}