lensonbocko's picture
First Push
2f0e33c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0635623931884766,
"min": 1.0635623931884766,
"max": 2.8703296184539795,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10119.7958984375,
"min": 10119.7958984375,
"max": 29552.9140625,
"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": 12.478067398071289,
"min": 0.19556096196174622,
"max": 12.478067398071289,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2433.22314453125,
"min": 37.93882751464844,
"max": 2513.22314453125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06892245911020677,
"min": 0.06072127071888198,
"max": 0.0742343491971648,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27568983644082706,
"min": 0.24288508287552793,
"max": 0.36995863856738614,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23000362267096836,
"min": 0.10867821811880989,
"max": 0.29331327704530136,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9200144906838734,
"min": 0.43471287247523954,
"max": 1.3619555909844006,
"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": 25.0,
"min": 3.25,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 143.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.25,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 143.0,
"max": 1342.0,
"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": "1701333713",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701334170"
},
"total": 456.980542515,
"count": 1,
"self": 0.7093833069999391,
"children": {
"run_training.setup": {
"total": 0.057922620999988794,
"count": 1,
"self": 0.057922620999988794
},
"TrainerController.start_learning": {
"total": 456.2132365870001,
"count": 1,
"self": 0.5352015249955002,
"children": {
"TrainerController._reset_env": {
"total": 4.1963995689999365,
"count": 1,
"self": 4.1963995689999365
},
"TrainerController.advance": {
"total": 451.35465277200467,
"count": 18204,
"self": 0.24775870600592498,
"children": {
"env_step": {
"total": 451.10689406599874,
"count": 18204,
"self": 305.2541820630029,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.5855729489988,
"count": 18204,
"self": 1.3978157499944928,
"children": {
"TorchPolicy.evaluate": {
"total": 144.1877571990043,
"count": 18204,
"self": 144.1877571990043
}
}
},
"workers": {
"total": 0.2671390539970844,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.96690136900156,
"count": 18204,
"is_parallel": true,
"self": 223.61240727701124,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006043551000061598,
"count": 1,
"is_parallel": true,
"self": 0.0037891050000098403,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022544460000517574,
"count": 10,
"is_parallel": true,
"self": 0.0022544460000517574
}
}
},
"UnityEnvironment.step": {
"total": 0.047294448000002376,
"count": 1,
"is_parallel": true,
"self": 0.0006032380000533522,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002475740000136284,
"count": 1,
"is_parallel": true,
"self": 0.0002475740000136284
},
"communicator.exchange": {
"total": 0.044338363999941066,
"count": 1,
"is_parallel": true,
"self": 0.044338363999941066
},
"steps_from_proto": {
"total": 0.0021052719999943292,
"count": 1,
"is_parallel": true,
"self": 0.00034842300033233187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017568489996619974,
"count": 10,
"is_parallel": true,
"self": 0.0017568489996619974
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.35449409199032,
"count": 18203,
"is_parallel": true,
"self": 10.28997367498755,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.140304195990211,
"count": 18203,
"is_parallel": true,
"self": 5.140304195990211
},
"communicator.exchange": {
"total": 183.5966562660077,
"count": 18203,
"is_parallel": true,
"self": 183.5966562660077
},
"steps_from_proto": {
"total": 32.32755995500486,
"count": 18203,
"is_parallel": true,
"self": 5.875288769025019,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.45227118597984,
"count": 182030,
"is_parallel": true,
"self": 26.45227118597984
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001380310000058671,
"count": 1,
"self": 0.0001380310000058671,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.5370507130002,
"count": 473197,
"is_parallel": true,
"self": 9.99991315701459,
"children": {
"process_trajectory": {
"total": 253.1506142779857,
"count": 473197,
"is_parallel": true,
"self": 252.51430511198566,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6363091660000464,
"count": 4,
"is_parallel": true,
"self": 0.6363091660000464
}
}
},
"_update_policy": {
"total": 184.3865232779999,
"count": 90,
"is_parallel": true,
"self": 55.77316257199925,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.61336070600066,
"count": 4587,
"is_parallel": true,
"self": 128.61336070600066
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12684468999998444,
"count": 1,
"self": 0.0011572720000003756,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12568741799998406,
"count": 1,
"self": 0.12568741799998406
}
}
}
}
}
}
}