Rudolph314's picture
Colab Trained
a49d83c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9524472951889038,
"min": 0.9524472951889038,
"max": 2.8628251552581787,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9093.966796875,
"min": 9093.966796875,
"max": 29318.193359375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.06943130493164,
"min": 0.26473385095596313,
"max": 13.06943130493164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.5390625,
"min": 51.358367919921875,
"max": 2659.462890625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07114046527695951,
"min": 0.06349292418956026,
"max": 0.0774096542502258,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28456186110783804,
"min": 0.25397169675824105,
"max": 0.38704827125112906,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1982772022339643,
"min": 0.10713081523164303,
"max": 0.2873783621133542,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7931088089358572,
"min": 0.4285232609265721,
"max": 1.4368918105667712,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 2.9318181818181817,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 129.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 2.9318181818181817,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 129.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713259662",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1713260099"
},
"total": 437.49415311999996,
"count": 1,
"self": 0.43519765099972574,
"children": {
"run_training.setup": {
"total": 0.05538020300014068,
"count": 1,
"self": 0.05538020300014068
},
"TrainerController.start_learning": {
"total": 437.0035752660001,
"count": 1,
"self": 0.5452460479850743,
"children": {
"TrainerController._reset_env": {
"total": 2.812703339000109,
"count": 1,
"self": 2.812703339000109
},
"TrainerController.advance": {
"total": 433.5538026200147,
"count": 18199,
"self": 0.25434341501249946,
"children": {
"env_step": {
"total": 433.2994592050022,
"count": 18199,
"self": 279.4911567229715,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.53233382001508,
"count": 18199,
"self": 1.42245421402572,
"children": {
"TorchPolicy.evaluate": {
"total": 152.10987960598936,
"count": 18199,
"self": 152.10987960598936
}
}
},
"workers": {
"total": 0.2759686620156572,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.9161778500229,
"count": 18199,
"is_parallel": true,
"self": 218.1331920340233,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008351724000021932,
"count": 1,
"is_parallel": true,
"self": 0.0066454699999667355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017062540000551962,
"count": 10,
"is_parallel": true,
"self": 0.0017062540000551962
}
}
},
"UnityEnvironment.step": {
"total": 0.037694448000138436,
"count": 1,
"is_parallel": true,
"self": 0.0007040600000891573,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004217809998863231,
"count": 1,
"is_parallel": true,
"self": 0.0004217809998863231
},
"communicator.exchange": {
"total": 0.0344952180000746,
"count": 1,
"is_parallel": true,
"self": 0.0344952180000746
},
"steps_from_proto": {
"total": 0.002073389000088355,
"count": 1,
"is_parallel": true,
"self": 0.00039999500017984246,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016733939999085123,
"count": 10,
"is_parallel": true,
"self": 0.0016733939999085123
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.7829858159996,
"count": 18198,
"is_parallel": true,
"self": 10.142927710971435,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.283297616009804,
"count": 18198,
"is_parallel": true,
"self": 5.283297616009804
},
"communicator.exchange": {
"total": 169.86639223001202,
"count": 18198,
"is_parallel": true,
"self": 169.86639223001202
},
"steps_from_proto": {
"total": 32.490368259006345,
"count": 18198,
"is_parallel": true,
"self": 5.972323913986202,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.518044345020144,
"count": 181980,
"is_parallel": true,
"self": 26.518044345020144
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012278300005164056,
"count": 1,
"self": 0.00012278300005164056,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 428.1681887901527,
"count": 664865,
"is_parallel": true,
"self": 13.686935299213019,
"children": {
"process_trajectory": {
"total": 235.23192076193982,
"count": 664865,
"is_parallel": true,
"self": 234.47731644494002,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7546043169998029,
"count": 4,
"is_parallel": true,
"self": 0.7546043169998029
}
}
},
"_update_policy": {
"total": 179.2493327289999,
"count": 90,
"is_parallel": true,
"self": 52.97001418400191,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.27931854499798,
"count": 4587,
"is_parallel": true,
"self": 126.27931854499798
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09170047600014186,
"count": 1,
"self": 0.0012777639999512758,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09042271200019059,
"count": 1,
"self": 0.09042271200019059
}
}
}
}
}
}
}