happyxujin's picture
First Push
2eccb86 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9576126933097839,
"min": 0.9576126933097839,
"max": 2.873276710510254,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9185.4208984375,
"min": 9185.4208984375,
"max": 29456.83203125,
"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": 13.034162521362305,
"min": 0.28085726499557495,
"max": 13.034162521362305,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2541.66162109375,
"min": 54.48630905151367,
"max": 2662.606201171875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0719169529746104,
"min": 0.06367154928739183,
"max": 0.07568999851138478,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2876678118984416,
"min": 0.2546861971495673,
"max": 0.37844999255692385,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19244463643168702,
"min": 0.12659361540778155,
"max": 0.28989122917546944,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7697785457267481,
"min": 0.5063744616311262,
"max": 1.4145503602191514,
"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": 25.65909090909091,
"min": 3.340909090909091,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 147.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.340909090909091,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 147.0,
"max": 1401.0,
"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": "1707179935",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707180432"
},
"total": 497.004191505,
"count": 1,
"self": 0.7518377330000021,
"children": {
"run_training.setup": {
"total": 0.05130990500003918,
"count": 1,
"self": 0.05130990500003918
},
"TrainerController.start_learning": {
"total": 496.20104386699995,
"count": 1,
"self": 0.68054838599096,
"children": {
"TrainerController._reset_env": {
"total": 3.171333417000028,
"count": 1,
"self": 3.171333417000028
},
"TrainerController.advance": {
"total": 492.197102933009,
"count": 18208,
"self": 0.33383006999372355,
"children": {
"env_step": {
"total": 491.86327286301525,
"count": 18208,
"self": 322.43082532798223,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.94642285701434,
"count": 18208,
"self": 1.6751536320085734,
"children": {
"TorchPolicy.evaluate": {
"total": 167.27126922500577,
"count": 18208,
"self": 167.27126922500577
}
}
},
"workers": {
"total": 0.4860246780186799,
"count": 18208,
"self": 0.0,
"children": {
"worker_root": {
"total": 494.7326091509917,
"count": 18208,
"is_parallel": true,
"self": 240.98077663498987,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0058673519999956625,
"count": 1,
"is_parallel": true,
"self": 0.004279723999957241,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015876280000384213,
"count": 10,
"is_parallel": true,
"self": 0.0015876280000384213
}
}
},
"UnityEnvironment.step": {
"total": 0.03901232400005483,
"count": 1,
"is_parallel": true,
"self": 0.0007006400001046131,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004410029999917242,
"count": 1,
"is_parallel": true,
"self": 0.0004410029999917242
},
"communicator.exchange": {
"total": 0.03571185600003446,
"count": 1,
"is_parallel": true,
"self": 0.03571185600003446
},
"steps_from_proto": {
"total": 0.002158824999924036,
"count": 1,
"is_parallel": true,
"self": 0.0003922600002397303,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017665649996843058,
"count": 10,
"is_parallel": true,
"self": 0.0017665649996843058
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.75183251600185,
"count": 18207,
"is_parallel": true,
"self": 11.834478077998938,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.08268702301325,
"count": 18207,
"is_parallel": true,
"self": 6.08268702301325
},
"communicator.exchange": {
"total": 198.7846805989991,
"count": 18207,
"is_parallel": true,
"self": 198.7846805989991
},
"steps_from_proto": {
"total": 37.049986815990565,
"count": 18207,
"is_parallel": true,
"self": 7.118249472004436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.93173734398613,
"count": 182070,
"is_parallel": true,
"self": 29.93173734398613
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016538599993509706,
"count": 1,
"self": 0.00016538599993509706,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 485.6686286181223,
"count": 741798,
"is_parallel": true,
"self": 16.102314703109414,
"children": {
"process_trajectory": {
"total": 268.1615303190122,
"count": 741798,
"is_parallel": true,
"self": 267.4235603030122,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7379700159999629,
"count": 4,
"is_parallel": true,
"self": 0.7379700159999629
}
}
},
"_update_policy": {
"total": 201.4047835960007,
"count": 90,
"is_parallel": true,
"self": 56.9102005879937,
"children": {
"TorchPPOOptimizer.update": {
"total": 144.494583008007,
"count": 4587,
"is_parallel": true,
"self": 144.494583008007
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15189374500005215,
"count": 1,
"self": 0.0015300220002245624,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1503637229998276,
"count": 1,
"self": 0.1503637229998276
}
}
}
}
}
}
}