Abbas110's picture
First training of SnowballTarget
1eb87c0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9273800849914551,
"min": 0.9273800849914551,
"max": 2.83011531829834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8813.8203125,
"min": 8813.8203125,
"max": 28889.81640625,
"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": 13.049629211425781,
"min": 0.3627171814441681,
"max": 13.049629211425781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2544.677734375,
"min": 70.36713409423828,
"max": 2654.03955078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06888856292318772,
"min": 0.057324000152042504,
"max": 0.07442005085770279,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2755542516927509,
"min": 0.22929600060817001,
"max": 0.36128372819318133,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.186193209798897,
"min": 0.13708485556108987,
"max": 0.302139525086272,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.744772839195588,
"min": 0.5483394222443595,
"max": 1.51069762543136,
"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": 25.636363636363637,
"min": 3.909090909090909,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 172.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.909090909090909,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 172.0,
"max": 1428.0,
"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": "1739288744",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739289176"
},
"total": 431.75128674000007,
"count": 1,
"self": 0.4404497050002192,
"children": {
"run_training.setup": {
"total": 0.02540958499980661,
"count": 1,
"self": 0.02540958499980661
},
"TrainerController.start_learning": {
"total": 431.28542745000004,
"count": 1,
"self": 0.3614578449955843,
"children": {
"TrainerController._reset_env": {
"total": 2.92613194799992,
"count": 1,
"self": 2.92613194799992
},
"TrainerController.advance": {
"total": 427.9092081870049,
"count": 18192,
"self": 0.36657062803556073,
"children": {
"env_step": {
"total": 304.8930279569961,
"count": 18192,
"self": 232.3160923369876,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.35896595999475,
"count": 18192,
"self": 1.291463848988542,
"children": {
"TorchPolicy.evaluate": {
"total": 71.0675021110062,
"count": 18192,
"self": 71.0675021110062
}
}
},
"workers": {
"total": 0.2179696600137504,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 429.6326967350044,
"count": 18192,
"is_parallel": true,
"self": 225.98287590400446,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005485506000013629,
"count": 1,
"is_parallel": true,
"self": 0.004044806000138124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014406999998755055,
"count": 10,
"is_parallel": true,
"self": 0.0014406999998755055
}
}
},
"UnityEnvironment.step": {
"total": 0.036693967000019256,
"count": 1,
"is_parallel": true,
"self": 0.0005806580002172268,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039210599993566575,
"count": 1,
"is_parallel": true,
"self": 0.00039210599993566575
},
"communicator.exchange": {
"total": 0.033775215999867214,
"count": 1,
"is_parallel": true,
"self": 0.033775215999867214
},
"steps_from_proto": {
"total": 0.0019459869999991497,
"count": 1,
"is_parallel": true,
"self": 0.00041142399982163624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015345630001775135,
"count": 10,
"is_parallel": true,
"self": 0.0015345630001775135
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.64982083099994,
"count": 18191,
"is_parallel": true,
"self": 9.603860791999523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.425183734007305,
"count": 18191,
"is_parallel": true,
"self": 5.425183734007305
},
"communicator.exchange": {
"total": 156.67815943197593,
"count": 18191,
"is_parallel": true,
"self": 156.67815943197593
},
"steps_from_proto": {
"total": 31.942616873017187,
"count": 18191,
"is_parallel": true,
"self": 5.7735720490168205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.169044824000366,
"count": 181910,
"is_parallel": true,
"self": 26.169044824000366
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.64960960197322,
"count": 18192,
"self": 0.4441133899590568,
"children": {
"process_trajectory": {
"total": 27.11806332301171,
"count": 18192,
"self": 26.57890591901173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5391574039999796,
"count": 4,
"self": 0.5391574039999796
}
}
},
"_update_policy": {
"total": 95.08743288900246,
"count": 90,
"self": 38.07146419500418,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.015968693998275,
"count": 4587,
"self": 57.015968693998275
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.63999809755478e-07,
"count": 1,
"self": 9.63999809755478e-07
},
"TrainerController._save_models": {
"total": 0.08862850599984995,
"count": 1,
"self": 0.0009902189999593247,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08763828699989062,
"count": 1,
"self": 0.08763828699989062
}
}
}
}
}
}
}