sajelian's picture
init
f1713e6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.803795576095581,
"min": 0.803795576095581,
"max": 2.86051607131958,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7639.27294921875,
"min": 7639.27294921875,
"max": 29200.1484375,
"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": 13.09008502960205,
"min": 0.2764233648777008,
"max": 13.09008502960205,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.566650390625,
"min": 53.62613296508789,
"max": 2643.687255859375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0742905608494766,
"min": 0.06268346270411641,
"max": 0.0742905608494766,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2971622433979064,
"min": 0.25287962596128494,
"max": 0.36976946652501674,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18980416009093035,
"min": 0.14478994480119653,
"max": 0.3044482460793327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7592166403637214,
"min": 0.5791597792047861,
"max": 1.4253112074791217,
"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": 25.5,
"min": 3.8181818181818183,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 168.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.8181818181818183,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 168.0,
"max": 1418.0,
"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": "1751143371",
"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": "1751143790"
},
"total": 418.4550966590001,
"count": 1,
"self": 0.4365371110001206,
"children": {
"run_training.setup": {
"total": 0.022946283000010226,
"count": 1,
"self": 0.022946283000010226
},
"TrainerController.start_learning": {
"total": 417.995613265,
"count": 1,
"self": 0.31618332898335666,
"children": {
"TrainerController._reset_env": {
"total": 3.7288595360000727,
"count": 1,
"self": 3.7288595360000727
},
"TrainerController.advance": {
"total": 413.87259048401654,
"count": 18192,
"self": 0.3557462570104235,
"children": {
"env_step": {
"total": 293.050445678017,
"count": 18192,
"self": 225.07038034401717,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.77956505799989,
"count": 18192,
"self": 1.1916874170091205,
"children": {
"TorchPolicy.evaluate": {
"total": 66.58787764099077,
"count": 18192,
"self": 66.58787764099077
}
}
},
"workers": {
"total": 0.200500275999957,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.67309249901473,
"count": 18192,
"is_parallel": true,
"self": 218.63977927901237,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0055564279999771315,
"count": 1,
"is_parallel": true,
"self": 0.00407116499991389,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014852630000632416,
"count": 10,
"is_parallel": true,
"self": 0.0014852630000632416
}
}
},
"UnityEnvironment.step": {
"total": 0.04726478700001735,
"count": 1,
"is_parallel": true,
"self": 0.0005983730001162257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004034759999740345,
"count": 1,
"is_parallel": true,
"self": 0.0004034759999740345
},
"communicator.exchange": {
"total": 0.04433902199991735,
"count": 1,
"is_parallel": true,
"self": 0.04433902199991735
},
"steps_from_proto": {
"total": 0.00192391600000974,
"count": 1,
"is_parallel": true,
"self": 0.0003869139999324034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015370020000773366,
"count": 10,
"is_parallel": true,
"self": 0.0015370020000773366
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 198.03331322000236,
"count": 18191,
"is_parallel": true,
"self": 9.773030596999433,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.223786373991743,
"count": 18191,
"is_parallel": true,
"self": 5.223786373991743
},
"communicator.exchange": {
"total": 152.1916631740063,
"count": 18191,
"is_parallel": true,
"self": 152.1916631740063
},
"steps_from_proto": {
"total": 30.844833075004885,
"count": 18191,
"is_parallel": true,
"self": 5.431192319974457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.41364075503043,
"count": 181910,
"is_parallel": true,
"self": 25.41364075503043
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.4663985489891,
"count": 18192,
"self": 0.40271315497739124,
"children": {
"process_trajectory": {
"total": 25.560307609011033,
"count": 18192,
"self": 25.171304032010653,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3890035770003806,
"count": 4,
"self": 0.3890035770003806
}
}
},
"_update_policy": {
"total": 94.50337778500068,
"count": 90,
"self": 39.90362889299877,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.59974889200191,
"count": 4587,
"self": 54.59974889200191
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.010000212583691e-07,
"count": 1,
"self": 9.010000212583691e-07
},
"TrainerController._save_models": {
"total": 0.07797901499998261,
"count": 1,
"self": 0.000758977000032246,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07722003799995036,
"count": 1,
"self": 0.07722003799995036
}
}
}
}
}
}
}