ArkenB's picture
First Push
2b888ed verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.90374755859375,
"min": 0.90374755859375,
"max": 2.840679407119751,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8589.216796875,
"min": 8589.216796875,
"max": 28997.65625,
"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": 13.091796875,
"min": 0.4571037292480469,
"max": 13.091796875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.900390625,
"min": 88.6781234741211,
"max": 2630.236328125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06698744429113325,
"min": 0.05904030933674863,
"max": 0.07913682556770486,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.267949777164533,
"min": 0.23908853498127713,
"max": 0.3956841278385243,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18904050275245135,
"min": 0.13677067970902676,
"max": 0.2708522267201368,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7561620110098054,
"min": 0.547082718836107,
"max": 1.354261133600684,
"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": 26.09090909090909,
"min": 3.5681818181818183,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1148.0,
"min": 157.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.09090909090909,
"min": 3.5681818181818183,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1148.0,
"min": 157.0,
"max": 1409.0,
"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": "1754318144",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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": "1.2.0.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": "1754318577"
},
"total": 432.70256045200006,
"count": 1,
"self": 0.6072625159999916,
"children": {
"run_training.setup": {
"total": 0.0209340210000164,
"count": 1,
"self": 0.0209340210000164
},
"TrainerController.start_learning": {
"total": 432.07436391500005,
"count": 1,
"self": 0.3735179199969707,
"children": {
"TrainerController._reset_env": {
"total": 3.3941255199999887,
"count": 1,
"self": 3.3941255199999887
},
"TrainerController.advance": {
"total": 428.1716510620032,
"count": 18192,
"self": 0.3720386270023255,
"children": {
"env_step": {
"total": 306.84768463800174,
"count": 18192,
"self": 235.55500041100936,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.07083654299345,
"count": 18192,
"self": 1.2992872199910153,
"children": {
"TorchPolicy.evaluate": {
"total": 69.77154932300243,
"count": 18192,
"self": 69.77154932300243
}
}
},
"workers": {
"total": 0.22184768399893073,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.4736736169831,
"count": 18192,
"is_parallel": true,
"self": 224.0437168710057,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005877320999957192,
"count": 1,
"is_parallel": true,
"self": 0.0038030909998951756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002074230000062016,
"count": 10,
"is_parallel": true,
"self": 0.002074230000062016
}
}
},
"UnityEnvironment.step": {
"total": 0.03846132699993632,
"count": 1,
"is_parallel": true,
"self": 0.0006813949997876989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047305300006428297,
"count": 1,
"is_parallel": true,
"self": 0.00047305300006428297
},
"communicator.exchange": {
"total": 0.035301632000027894,
"count": 1,
"is_parallel": true,
"self": 0.035301632000027894
},
"steps_from_proto": {
"total": 0.0020052470000564426,
"count": 1,
"is_parallel": true,
"self": 0.00038565399972867453,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001619593000327768,
"count": 10,
"is_parallel": true,
"self": 0.001619593000327768
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.4299567459774,
"count": 18191,
"is_parallel": true,
"self": 10.046316965981532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.549600827003928,
"count": 18191,
"is_parallel": true,
"self": 5.549600827003928
},
"communicator.exchange": {
"total": 158.0162552260058,
"count": 18191,
"is_parallel": true,
"self": 158.0162552260058
},
"steps_from_proto": {
"total": 32.817783726986136,
"count": 18191,
"is_parallel": true,
"self": 5.9399988460342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.877784880951936,
"count": 181910,
"is_parallel": true,
"self": 26.877784880951936
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.95192779699914,
"count": 18192,
"self": 0.4360764369965864,
"children": {
"process_trajectory": {
"total": 27.630321049002532,
"count": 18192,
"self": 27.1236717890024,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5066492600001311,
"count": 4,
"self": 0.5066492600001311
}
}
},
"_update_policy": {
"total": 92.88553031100002,
"count": 90,
"self": 38.37967249001713,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.5058578209829,
"count": 4587,
"self": 54.5058578209829
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.419000000169035e-06,
"count": 1,
"self": 1.419000000169035e-06
},
"TrainerController._save_models": {
"total": 0.13506799399988267,
"count": 1,
"self": 0.001202217999889399,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13386577599999328,
"count": 1,
"self": 0.13386577599999328
}
}
}
}
}
}
}