AlGM93's picture
Baseline Training.
94b0de2 verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9348503351211548,
"min": 0.9348503351211548,
"max": 2.8777260780334473,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8936.234375,
"min": 8936.234375,
"max": 29470.79296875,
"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": 12.827789306640625,
"min": 0.24623343348503113,
"max": 12.839905738830566,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2501.4189453125,
"min": 47.769287109375,
"max": 2619.3408203125,
"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": 0.07136065754806908,
"min": 0.06111594449227113,
"max": 0.07295085982278027,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28544263019227634,
"min": 0.24446377796908453,
"max": 0.36475429911390134,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1887068257247116,
"min": 0.11989114010551324,
"max": 0.26799963362076695,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7548273028988464,
"min": 0.479564560422053,
"max": 1.3399981681038349,
"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": 25.386363636363637,
"min": 3.0681818181818183,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 135.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.0681818181818183,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 135.0,
"max": 1387.0,
"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": "1709030196",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709030674"
},
"total": 477.5065828559999,
"count": 1,
"self": 0.4379560819998005,
"children": {
"run_training.setup": {
"total": 0.046337423000068156,
"count": 1,
"self": 0.046337423000068156
},
"TrainerController.start_learning": {
"total": 477.02228935100004,
"count": 1,
"self": 0.6185605900157043,
"children": {
"TrainerController._reset_env": {
"total": 3.1346293039999864,
"count": 1,
"self": 3.1346293039999864
},
"TrainerController.advance": {
"total": 473.1609438489843,
"count": 18200,
"self": 0.29607905997158923,
"children": {
"env_step": {
"total": 472.8648647890127,
"count": 18200,
"self": 305.14544850800974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.41164061499933,
"count": 18200,
"self": 1.606771139994862,
"children": {
"TorchPolicy.evaluate": {
"total": 165.80486947500447,
"count": 18200,
"self": 165.80486947500447
}
}
},
"workers": {
"total": 0.3077756660036357,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 475.7215515939944,
"count": 18200,
"is_parallel": true,
"self": 237.8217985429991,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0060488169999644015,
"count": 1,
"is_parallel": true,
"self": 0.004340334999710649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017084820002537526,
"count": 10,
"is_parallel": true,
"self": 0.0017084820002537526
}
}
},
"UnityEnvironment.step": {
"total": 0.04242289100000107,
"count": 1,
"is_parallel": true,
"self": 0.0006183469999996305,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004795010000862021,
"count": 1,
"is_parallel": true,
"self": 0.0004795010000862021
},
"communicator.exchange": {
"total": 0.03923985599999469,
"count": 1,
"is_parallel": true,
"self": 0.03923985599999469
},
"steps_from_proto": {
"total": 0.002085186999920552,
"count": 1,
"is_parallel": true,
"self": 0.0004089409999323834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016762459999881685,
"count": 10,
"is_parallel": true,
"self": 0.0016762459999881685
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.8997530509953,
"count": 18199,
"is_parallel": true,
"self": 11.0149467509533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.924105787005715,
"count": 18199,
"is_parallel": true,
"self": 5.924105787005715
},
"communicator.exchange": {
"total": 183.60746111500657,
"count": 18199,
"is_parallel": true,
"self": 183.60746111500657
},
"steps_from_proto": {
"total": 37.3532393980297,
"count": 18199,
"is_parallel": true,
"self": 6.913492293040576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.439747104989124,
"count": 181990,
"is_parallel": true,
"self": 30.439747104989124
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.193399990981561e-05,
"count": 1,
"self": 4.193399990981561e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 466.94216036490945,
"count": 717092,
"is_parallel": true,
"self": 15.908026561852694,
"children": {
"process_trajectory": {
"total": 258.15858498505725,
"count": 717092,
"is_parallel": true,
"self": 257.60512922205726,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5534557629999881,
"count": 4,
"is_parallel": true,
"self": 0.5534557629999881
}
}
},
"_update_policy": {
"total": 192.87554881799952,
"count": 90,
"is_parallel": true,
"self": 54.96702227200103,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.90852654599848,
"count": 4584,
"is_parallel": true,
"self": 137.90852654599848
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10811367400015115,
"count": 1,
"self": 0.000952944000118805,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10716073000003234,
"count": 1,
"self": 0.10716073000003234
}
}
}
}
}
}
}