johnnyluhk's picture
First Push
c2cd8f0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8694990873336792,
"min": 0.8694990873336792,
"max": 2.861798048019409,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8301.9775390625,
"min": 8301.9775390625,
"max": 29307.673828125,
"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": 13.125223159790039,
"min": 0.3941713273525238,
"max": 13.125223159790039,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.41845703125,
"min": 76.46923828125,
"max": 2669.6884765625,
"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": 0.06290818384150043,
"min": 0.06290818384150043,
"max": 0.07913074261366501,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2516327353660017,
"min": 0.2516327353660017,
"max": 0.3629522450318487,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18744806302528755,
"min": 0.14344497179548601,
"max": 0.28458108928273707,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7497922521011502,
"min": 0.5737798871819441,
"max": 1.3597476064574483,
"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": 25.772727272727273,
"min": 3.840909090909091,
"max": 26.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 169.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.840909090909091,
"max": 26.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 169.0,
"max": 1419.0,
"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": "1710124762",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710125229"
},
"total": 466.46043809899993,
"count": 1,
"self": 0.4339733760002673,
"children": {
"run_training.setup": {
"total": 0.058360373999676085,
"count": 1,
"self": 0.058360373999676085
},
"TrainerController.start_learning": {
"total": 465.968104349,
"count": 1,
"self": 0.607229557982464,
"children": {
"TrainerController._reset_env": {
"total": 2.8518438030000652,
"count": 1,
"self": 2.8518438030000652
},
"TrainerController.advance": {
"total": 462.40913772401746,
"count": 18199,
"self": 0.288946644047428,
"children": {
"env_step": {
"total": 462.12019107997,
"count": 18199,
"self": 301.1433281729992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.45343934099628,
"count": 18199,
"self": 1.5489211419967432,
"children": {
"TorchPolicy.evaluate": {
"total": 158.90451819899954,
"count": 18199,
"self": 158.90451819899954
}
}
},
"workers": {
"total": 0.5234235659745536,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.5990348169653,
"count": 18199,
"is_parallel": true,
"self": 229.9929255469533,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00555130199973064,
"count": 1,
"is_parallel": true,
"self": 0.003764923000289855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017863789994407853,
"count": 10,
"is_parallel": true,
"self": 0.0017863789994407853
}
}
},
"UnityEnvironment.step": {
"total": 0.040150893999907566,
"count": 1,
"is_parallel": true,
"self": 0.0007139089998418058,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003884090001520235,
"count": 1,
"is_parallel": true,
"self": 0.0003884090001520235
},
"communicator.exchange": {
"total": 0.03691994500013607,
"count": 1,
"is_parallel": true,
"self": 0.03691994500013607
},
"steps_from_proto": {
"total": 0.00212863099977767,
"count": 1,
"is_parallel": true,
"self": 0.00038568799891436356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017429430008633062,
"count": 10,
"is_parallel": true,
"self": 0.0017429430008633062
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.60610927001198,
"count": 18198,
"is_parallel": true,
"self": 10.772940961973745,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.513848628038431,
"count": 18198,
"is_parallel": true,
"self": 5.513848628038431
},
"communicator.exchange": {
"total": 183.30787488301894,
"count": 18198,
"is_parallel": true,
"self": 183.30787488301894
},
"steps_from_proto": {
"total": 35.01144479698087,
"count": 18198,
"is_parallel": true,
"self": 6.7080609289723725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.303383868008495,
"count": 181980,
"is_parallel": true,
"self": 28.303383868008495
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014185400004862458,
"count": 1,
"self": 0.00014185400004862458,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.15320085782196,
"count": 699762,
"is_parallel": true,
"self": 15.579775170853736,
"children": {
"process_trajectory": {
"total": 251.90720610596827,
"count": 699762,
"is_parallel": true,
"self": 251.3907724169685,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5164336889997685,
"count": 4,
"is_parallel": true,
"self": 0.5164336889997685
}
}
},
"_update_policy": {
"total": 188.66621958099995,
"count": 90,
"is_parallel": true,
"self": 54.42400334000786,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.2422162409921,
"count": 4587,
"is_parallel": true,
"self": 134.2422162409921
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09975140999995347,
"count": 1,
"self": 0.000969908000115538,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09878150199983793,
"count": 1,
"self": 0.09878150199983793
}
}
}
}
}
}
}