mikedad's picture
First training of SnowballTarger
85303f9
raw
history blame contribute delete
No virus
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.890850841999054,
"min": 0.890850841999054,
"max": 2.87168025970459,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8505.84375,
"min": 8505.84375,
"max": 29408.876953125,
"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": 12.799067497253418,
"min": 0.41526415944099426,
"max": 12.799067497253418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2495.818115234375,
"min": 80.56124877929688,
"max": 2593.13671875,
"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": 0.06630222325585754,
"min": 0.06516417337415452,
"max": 0.07823824073763236,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26520889302343015,
"min": 0.2606566934966181,
"max": 0.3790210647093059,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1939488827597861,
"min": 0.09672713907339665,
"max": 0.2759883687922768,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7757955310391444,
"min": 0.3869085562935866,
"max": 1.3330342746248434,
"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": 25.136363636363637,
"min": 2.8636363636363638,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 126.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 2.8636363636363638,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 126.0,
"max": 1398.0,
"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": "1703601215",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703601688"
},
"total": 472.436323322,
"count": 1,
"self": 0.448878757999978,
"children": {
"run_training.setup": {
"total": 0.04948775200000455,
"count": 1,
"self": 0.04948775200000455
},
"TrainerController.start_learning": {
"total": 471.93795681200004,
"count": 1,
"self": 0.6628677100057985,
"children": {
"TrainerController._reset_env": {
"total": 3.036529478000034,
"count": 1,
"self": 3.036529478000034
},
"TrainerController.advance": {
"total": 468.14602101599417,
"count": 18199,
"self": 0.3030822690033119,
"children": {
"env_step": {
"total": 467.84293874699085,
"count": 18199,
"self": 307.77839409299247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.74993695101216,
"count": 18199,
"self": 1.5903962210185227,
"children": {
"TorchPolicy.evaluate": {
"total": 158.15954072999364,
"count": 18199,
"self": 158.15954072999364
}
}
},
"workers": {
"total": 0.31460770298622265,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 470.55344634300184,
"count": 18199,
"is_parallel": true,
"self": 230.8238946260094,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004667187000109152,
"count": 1,
"is_parallel": true,
"self": 0.003269400000249334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001397786999859818,
"count": 10,
"is_parallel": true,
"self": 0.001397786999859818
}
}
},
"UnityEnvironment.step": {
"total": 0.03848376600001302,
"count": 1,
"is_parallel": true,
"self": 0.0007112649999498899,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004355130000703866,
"count": 1,
"is_parallel": true,
"self": 0.0004355130000703866
},
"communicator.exchange": {
"total": 0.035147462000054475,
"count": 1,
"is_parallel": true,
"self": 0.035147462000054475
},
"steps_from_proto": {
"total": 0.002189525999938269,
"count": 1,
"is_parallel": true,
"self": 0.0006263329999001144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015631930000381544,
"count": 10,
"is_parallel": true,
"self": 0.0015631930000381544
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.72955171699243,
"count": 18198,
"is_parallel": true,
"self": 10.988354425963735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.7170982489979,
"count": 18198,
"is_parallel": true,
"self": 5.7170982489979
},
"communicator.exchange": {
"total": 187.2864321350271,
"count": 18198,
"is_parallel": true,
"self": 187.2864321350271
},
"steps_from_proto": {
"total": 35.7376669070037,
"count": 18198,
"is_parallel": true,
"self": 6.712550446012983,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.025116460990716,
"count": 181980,
"is_parallel": true,
"self": 29.025116460990716
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014113500014900637,
"count": 1,
"self": 0.00014113500014900637,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.15976864002914,
"count": 718800,
"is_parallel": true,
"self": 15.211670404935035,
"children": {
"process_trajectory": {
"total": 255.81544102409384,
"count": 718800,
"is_parallel": true,
"self": 255.1928443570937,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6225966670001526,
"count": 5,
"is_parallel": true,
"self": 0.6225966670001526
}
}
},
"_update_policy": {
"total": 191.13265721100026,
"count": 90,
"is_parallel": true,
"self": 58.223606260001816,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.90905095099845,
"count": 4584,
"is_parallel": true,
"self": 132.90905095099845
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09239747299989176,
"count": 1,
"self": 0.0009491409998645395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09144833200002722,
"count": 1,
"self": 0.09144833200002722
}
}
}
}
}
}
}