ricardoams's picture
First Push
0acc28e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0238502025604248,
"min": 1.0238502025604248,
"max": 2.869971752166748,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9809.5087890625,
"min": 9809.5087890625,
"max": 29454.51953125,
"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": 11.947100639343262,
"min": 0.45694699883461,
"max": 11.947100639343262,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2329.6845703125,
"min": 88.64772033691406,
"max": 2423.88720703125,
"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": 0.06772170083023214,
"min": 0.055532096932937765,
"max": 0.0745276309627276,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27088680332092857,
"min": 0.22212838773175106,
"max": 0.3615225909298341,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23073163058827906,
"min": 0.11390838182905652,
"max": 0.2811936078702702,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9229265223531162,
"min": 0.4556335273162261,
"max": 1.3661669486877965,
"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": 23.795454545454547,
"min": 3.4318181818181817,
"max": 23.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1047.0,
"min": 151.0,
"max": 1275.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.795454545454547,
"min": 3.4318181818181817,
"max": 23.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1047.0,
"min": 151.0,
"max": 1275.0,
"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": "1715178217",
"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": "1715178843"
},
"total": 626.166013324,
"count": 1,
"self": 1.1219940549999592,
"children": {
"run_training.setup": {
"total": 0.07352959899998268,
"count": 1,
"self": 0.07352959899998268
},
"TrainerController.start_learning": {
"total": 624.97048967,
"count": 1,
"self": 0.920389188001991,
"children": {
"TrainerController._reset_env": {
"total": 3.138521719000039,
"count": 1,
"self": 3.138521719000039
},
"TrainerController.advance": {
"total": 620.7328616009981,
"count": 18209,
"self": 0.4368590539982051,
"children": {
"env_step": {
"total": 620.296002547,
"count": 18209,
"self": 480.92402409399307,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.92329973799986,
"count": 18209,
"self": 2.629964436995465,
"children": {
"TorchPolicy.evaluate": {
"total": 136.2933353010044,
"count": 18209,
"self": 136.2933353010044
}
}
},
"workers": {
"total": 0.44867871500701995,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 622.6996934319926,
"count": 18209,
"is_parallel": true,
"self": 286.40178298098454,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00627820500000098,
"count": 1,
"is_parallel": true,
"self": 0.004316542000140089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019616629998608914,
"count": 10,
"is_parallel": true,
"self": 0.0019616629998608914
}
}
},
"UnityEnvironment.step": {
"total": 0.044285996000041905,
"count": 1,
"is_parallel": true,
"self": 0.0006127970000306959,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005360479999581003,
"count": 1,
"is_parallel": true,
"self": 0.0005360479999581003
},
"communicator.exchange": {
"total": 0.04088320900001463,
"count": 1,
"is_parallel": true,
"self": 0.04088320900001463
},
"steps_from_proto": {
"total": 0.002253942000038478,
"count": 1,
"is_parallel": true,
"self": 0.0004287419998831865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018252000001552915,
"count": 10,
"is_parallel": true,
"self": 0.0018252000001552915
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 336.2979104510081,
"count": 18208,
"is_parallel": true,
"self": 16.10433250802106,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.184807946989793,
"count": 18208,
"is_parallel": true,
"self": 8.184807946989793
},
"communicator.exchange": {
"total": 264.6562295179954,
"count": 18208,
"is_parallel": true,
"self": 264.6562295179954
},
"steps_from_proto": {
"total": 47.3525404780018,
"count": 18208,
"is_parallel": true,
"self": 9.645651058003693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.706889419998106,
"count": 182080,
"is_parallel": true,
"self": 37.706889419998106
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000202703000013571,
"count": 1,
"self": 0.000202703000013571,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 613.7329355670208,
"count": 786524,
"is_parallel": true,
"self": 17.938800335976794,
"children": {
"process_trajectory": {
"total": 337.87940894304376,
"count": 786524,
"is_parallel": true,
"self": 336.92888543204396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9505235109998011,
"count": 4,
"is_parallel": true,
"self": 0.9505235109998011
}
}
},
"_update_policy": {
"total": 257.9147262880002,
"count": 90,
"is_parallel": true,
"self": 75.0955365469992,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.81918974100103,
"count": 4587,
"is_parallel": true,
"self": 182.81918974100103
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17851445899987084,
"count": 1,
"self": 0.0034460009999293106,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17506845799994153,
"count": 1,
"self": 0.17506845799994153
}
}
}
}
}
}
}