AryanPakdel's picture
First Push
cb1b6b7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9154772758483887,
"min": 0.9154772758483887,
"max": 2.8664910793304443,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8700.6962890625,
"min": 8700.6962890625,
"max": 29261.140625,
"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": 12.000801086425781,
"min": 0.4499475657939911,
"max": 12.054278373718262,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2340.15625,
"min": 87.28982543945312,
"max": 2459.07275390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06865985929399875,
"min": 0.060402533613384615,
"max": 0.07452310860015346,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.274639437175995,
"min": 0.24875007213125297,
"max": 0.3571468566398264,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19432941652542235,
"min": 0.13373731216872292,
"max": 0.2857888880021432,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7773176661016894,
"min": 0.5349492486748917,
"max": 1.313244847690358,
"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": 23.477272727272727,
"min": 3.340909090909091,
"max": 23.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1033.0,
"min": 147.0,
"max": 1288.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.477272727272727,
"min": 3.340909090909091,
"max": 23.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1033.0,
"min": 147.0,
"max": 1288.0,
"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": "1758121355",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758121782"
},
"total": 427.034130106,
"count": 1,
"self": 0.6559927450000487,
"children": {
"run_training.setup": {
"total": 0.024707959000011215,
"count": 1,
"self": 0.024707959000011215
},
"TrainerController.start_learning": {
"total": 426.35342940199996,
"count": 1,
"self": 0.3794306089986321,
"children": {
"TrainerController._reset_env": {
"total": 2.946435349000012,
"count": 1,
"self": 2.946435349000012
},
"TrainerController.advance": {
"total": 422.90560351100135,
"count": 18192,
"self": 0.3974529810200238,
"children": {
"env_step": {
"total": 301.21162635598546,
"count": 18192,
"self": 232.61751644998856,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.36359421998952,
"count": 18192,
"self": 1.2640043569897443,
"children": {
"TorchPolicy.evaluate": {
"total": 67.09958986299978,
"count": 18192,
"self": 67.09958986299978
}
}
},
"workers": {
"total": 0.23051568600737937,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.78359433901085,
"count": 18192,
"is_parallel": true,
"self": 220.88385185700236,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005058313999938946,
"count": 1,
"is_parallel": true,
"self": 0.0036843660001295575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013739479998093884,
"count": 10,
"is_parallel": true,
"self": 0.0013739479998093884
}
}
},
"UnityEnvironment.step": {
"total": 0.03396546399994804,
"count": 1,
"is_parallel": true,
"self": 0.0005599009999741611,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040363400000842375,
"count": 1,
"is_parallel": true,
"self": 0.00040363400000842375
},
"communicator.exchange": {
"total": 0.03120259599995734,
"count": 1,
"is_parallel": true,
"self": 0.03120259599995734
},
"steps_from_proto": {
"total": 0.0017993330000081187,
"count": 1,
"is_parallel": true,
"self": 0.0003365210000083607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001462811999999758,
"count": 10,
"is_parallel": true,
"self": 0.001462811999999758
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.8997424820085,
"count": 18191,
"is_parallel": true,
"self": 9.787970412012442,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.285143546983022,
"count": 18191,
"is_parallel": true,
"self": 5.285143546983022
},
"communicator.exchange": {
"total": 157.84536427299565,
"count": 18191,
"is_parallel": true,
"self": 157.84536427299565
},
"steps_from_proto": {
"total": 30.981264250017375,
"count": 18191,
"is_parallel": true,
"self": 5.545470259968056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.43579399004932,
"count": 181910,
"is_parallel": true,
"self": 25.43579399004932
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.29652417399586,
"count": 18192,
"self": 0.46128638600021077,
"children": {
"process_trajectory": {
"total": 26.522404001995938,
"count": 18192,
"self": 26.05569222799602,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4667117739999185,
"count": 4,
"self": 0.4667117739999185
}
}
},
"_update_policy": {
"total": 94.31283378599971,
"count": 90,
"self": 38.56619789299168,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.74663589300803,
"count": 4587,
"self": 55.74663589300803
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3769999895885121e-06,
"count": 1,
"self": 1.3769999895885121e-06
},
"TrainerController._save_models": {
"total": 0.1219585559999814,
"count": 1,
"self": 0.001069946000143318,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12088860999983808,
"count": 1,
"self": 0.12088860999983808
}
}
}
}
}
}
}