kkyrulez01's picture
First training of SnowballTarget
a21590f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6764135956764221,
"min": 0.6764135956764221,
"max": 2.8419525623321533,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6428.634765625,
"min": 6428.634765625,
"max": 29010.65234375,
"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": 12.512227058410645,
"min": 0.3329909145832062,
"max": 12.512227058410645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2439.88427734375,
"min": 64.60023498535156,
"max": 2530.15087890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06278878429393266,
"min": 0.058868982857116045,
"max": 0.07418580133868519,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2511551371757306,
"min": 0.23547593142846418,
"max": 0.35205578521195363,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22457015485155818,
"min": 0.13466850992556953,
"max": 0.28930954681892024,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8982806194062327,
"min": 0.5386740397022781,
"max": 1.4465477340946011,
"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": 24.522727272727273,
"min": 3.5454545454545454,
"max": 24.6,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1079.0,
"min": 156.0,
"max": 1353.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.522727272727273,
"min": 3.5454545454545454,
"max": 24.6,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1079.0,
"min": 156.0,
"max": 1353.0,
"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": "1752153665",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752154102"
},
"total": 437.533945344,
"count": 1,
"self": 0.5446820400001116,
"children": {
"run_training.setup": {
"total": 0.02328137599999991,
"count": 1,
"self": 0.02328137599999991
},
"TrainerController.start_learning": {
"total": 436.9659819279999,
"count": 1,
"self": 0.34253186000080404,
"children": {
"TrainerController._reset_env": {
"total": 3.176570448999996,
"count": 1,
"self": 3.176570448999996
},
"TrainerController.advance": {
"total": 433.36098166199906,
"count": 18192,
"self": 0.38247955798931343,
"children": {
"env_step": {
"total": 308.24662143001046,
"count": 18192,
"self": 235.11483045201237,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.9226881759979,
"count": 18192,
"self": 1.2980947469969806,
"children": {
"TorchPolicy.evaluate": {
"total": 71.62459342900092,
"count": 18192,
"self": 71.62459342900092
}
}
},
"workers": {
"total": 0.2091028020001886,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.27993648001086,
"count": 18192,
"is_parallel": true,
"self": 229.4474919880065,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0075957010000138325,
"count": 1,
"is_parallel": true,
"self": 0.0061315019997891795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001464199000224653,
"count": 10,
"is_parallel": true,
"self": 0.001464199000224653
}
}
},
"UnityEnvironment.step": {
"total": 0.03924102300004506,
"count": 1,
"is_parallel": true,
"self": 0.0006250830000453789,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045543199996700423,
"count": 1,
"is_parallel": true,
"self": 0.00045543199996700423
},
"communicator.exchange": {
"total": 0.03615413099998932,
"count": 1,
"is_parallel": true,
"self": 0.03615413099998932
},
"steps_from_proto": {
"total": 0.002006377000043358,
"count": 1,
"is_parallel": true,
"self": 0.0003902610002342044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016161159998091534,
"count": 10,
"is_parallel": true,
"self": 0.0016161159998091534
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.83244449200436,
"count": 18191,
"is_parallel": true,
"self": 9.874733009997954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.628709933006462,
"count": 18191,
"is_parallel": true,
"self": 5.628709933006462
},
"communicator.exchange": {
"total": 157.60929971200198,
"count": 18191,
"is_parallel": true,
"self": 157.60929971200198
},
"steps_from_proto": {
"total": 32.719701836997956,
"count": 18191,
"is_parallel": true,
"self": 5.898468064991562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.821233772006394,
"count": 181910,
"is_parallel": true,
"self": 26.821233772006394
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.73188067399929,
"count": 18192,
"self": 0.4257530929968425,
"children": {
"process_trajectory": {
"total": 28.664766721002934,
"count": 18192,
"self": 28.24897032400304,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41579639699989457,
"count": 4,
"self": 0.41579639699989457
}
}
},
"_update_policy": {
"total": 95.64136085999951,
"count": 90,
"self": 38.88106682399632,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.76029403600319,
"count": 4587,
"self": 56.76029403600319
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6169999526027823e-06,
"count": 1,
"self": 1.6169999526027823e-06
},
"TrainerController._save_models": {
"total": 0.08589634000009028,
"count": 1,
"self": 0.0008696290001353191,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08502671099995496,
"count": 1,
"self": 0.08502671099995496
}
}
}
}
}
}
}