MoadJ's picture
First Push
156ca61 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9823093414306641,
"min": 0.962856113910675,
"max": 2.8641469478607178,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9335.8681640625,
"min": 9335.8681640625,
"max": 29237.2109375,
"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": 13.041555404663086,
"min": 0.5244159698486328,
"max": 13.041555404663086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.103271484375,
"min": 101.7366943359375,
"max": 2649.39453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07134842881450645,
"min": 0.06239762536247672,
"max": 0.07134842881450645,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2853937152580258,
"min": 0.24959050144990688,
"max": 0.353088468914304,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18963887710489477,
"min": 0.1455410367320748,
"max": 0.276918921342083,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7585555084195791,
"min": 0.5821641469282992,
"max": 1.3845946067104151,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.636363636363637,
"min": 3.7045454545454546,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 163.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.7045454545454546,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 163.0,
"max": 1404.0,
"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": "1752174227",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752174643"
},
"total": 415.91582121400006,
"count": 1,
"self": 0.43309933000000456,
"children": {
"run_training.setup": {
"total": 0.022972468000034496,
"count": 1,
"self": 0.022972468000034496
},
"TrainerController.start_learning": {
"total": 415.459749416,
"count": 1,
"self": 0.35024129100668233,
"children": {
"TrainerController._reset_env": {
"total": 3.4204933119999623,
"count": 1,
"self": 3.4204933119999623
},
"TrainerController.advance": {
"total": 411.6103886709931,
"count": 18192,
"self": 0.3728025539907094,
"children": {
"env_step": {
"total": 292.98517460100913,
"count": 18192,
"self": 224.37204956300866,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.40954095200323,
"count": 18192,
"self": 1.2085175780222244,
"children": {
"TorchPolicy.evaluate": {
"total": 67.201023373981,
"count": 18192,
"self": 67.201023373981
}
}
},
"workers": {
"total": 0.20358408599724953,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 414.11618844500106,
"count": 18192,
"is_parallel": true,
"self": 217.18866585399212,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052415740000242295,
"count": 1,
"is_parallel": true,
"self": 0.0038280569999642466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014135170000599828,
"count": 10,
"is_parallel": true,
"self": 0.0014135170000599828
}
}
},
"UnityEnvironment.step": {
"total": 0.03471296199995777,
"count": 1,
"is_parallel": true,
"self": 0.0005725019999545111,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041611500000726664,
"count": 1,
"is_parallel": true,
"self": 0.00041611500000726664
},
"communicator.exchange": {
"total": 0.03190996900002574,
"count": 1,
"is_parallel": true,
"self": 0.03190996900002574
},
"steps_from_proto": {
"total": 0.0018143759999702525,
"count": 1,
"is_parallel": true,
"self": 0.0003417369998715003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014726390000987521,
"count": 10,
"is_parallel": true,
"self": 0.0014726390000987521
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 196.92752259100894,
"count": 18191,
"is_parallel": true,
"self": 9.600203833974888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.155771102010021,
"count": 18191,
"is_parallel": true,
"self": 5.155771102010021
},
"communicator.exchange": {
"total": 151.81531755501896,
"count": 18191,
"is_parallel": true,
"self": 151.81531755501896
},
"steps_from_proto": {
"total": 30.356230100005064,
"count": 18191,
"is_parallel": true,
"self": 5.403048367981569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.953181732023495,
"count": 181910,
"is_parallel": true,
"self": 24.953181732023495
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.25241151599323,
"count": 18192,
"self": 0.4326343169905158,
"children": {
"process_trajectory": {
"total": 25.665562002002275,
"count": 18192,
"self": 25.23139146500239,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4341705369998863,
"count": 4,
"self": 0.4341705369998863
}
}
},
"_update_policy": {
"total": 92.15421519700044,
"count": 90,
"self": 37.56846265900185,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.58575253799859,
"count": 4587,
"self": 54.58575253799859
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.670001534483163e-07,
"count": 1,
"self": 8.670001534483163e-07
},
"TrainerController._save_models": {
"total": 0.07862527500014949,
"count": 1,
"self": 0.0008287830000881513,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07779649200006133,
"count": 1,
"self": 0.07779649200006133
}
}
}
}
}
}
}