danmorris427's picture
First Push
d43a50d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0350844860076904,
"min": 1.0350844860076904,
"max": 2.8463785648345947,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9882.986328125,
"min": 9882.986328125,
"max": 29149.76171875,
"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": 11.915590286254883,
"min": 0.3093089759349823,
"max": 11.915590286254883,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2323.5400390625,
"min": 60.005943298339844,
"max": 2411.0908203125,
"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": 0.06667853149723241,
"min": 0.06258233416158998,
"max": 0.07578382708087184,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26671412598892963,
"min": 0.2507595892655481,
"max": 0.3530162227289824,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1877655232799988,
"min": 0.10393385825149129,
"max": 0.26312092583553465,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7510620931199952,
"min": 0.41573543300596516,
"max": 1.3156046291776733,
"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": 23.09090909090909,
"min": 2.977272727272727,
"max": 23.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1016.0,
"min": 131.0,
"max": 1304.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.09090909090909,
"min": 2.977272727272727,
"max": 23.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1016.0,
"min": 131.0,
"max": 1304.0,
"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": "1674438983",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674439402"
},
"total": 419.400113174,
"count": 1,
"self": 0.39786291900003334,
"children": {
"run_training.setup": {
"total": 0.10602241399999457,
"count": 1,
"self": 0.10602241399999457
},
"TrainerController.start_learning": {
"total": 418.896227841,
"count": 1,
"self": 0.5284926040055211,
"children": {
"TrainerController._reset_env": {
"total": 8.985732568999993,
"count": 1,
"self": 8.985732568999993
},
"TrainerController.advance": {
"total": 409.26503339599435,
"count": 18201,
"self": 0.3027528949899647,
"children": {
"env_step": {
"total": 408.9622805010044,
"count": 18201,
"self": 268.2585602099942,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.43900143100774,
"count": 18201,
"self": 1.351880772006723,
"children": {
"TorchPolicy.evaluate": {
"total": 139.08712065900102,
"count": 18201,
"self": 30.762622354012308,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.32449830498871,
"count": 18201,
"self": 108.32449830498871
}
}
}
}
},
"workers": {
"total": 0.2647188600024606,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 417.70556920100086,
"count": 18201,
"is_parallel": true,
"self": 199.24856550800206,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007549172999972598,
"count": 1,
"is_parallel": true,
"self": 0.005182052999941789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002367120000030809,
"count": 10,
"is_parallel": true,
"self": 0.002367120000030809
}
}
},
"UnityEnvironment.step": {
"total": 0.03931010400003743,
"count": 1,
"is_parallel": true,
"self": 0.0004168359999994209,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003590180000401233,
"count": 1,
"is_parallel": true,
"self": 0.0003590180000401233
},
"communicator.exchange": {
"total": 0.03711299799999779,
"count": 1,
"is_parallel": true,
"self": 0.03711299799999779
},
"steps_from_proto": {
"total": 0.001421252000000095,
"count": 1,
"is_parallel": true,
"self": 0.00036808899994866806,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001053163000051427,
"count": 10,
"is_parallel": true,
"self": 0.001053163000051427
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.4570036929988,
"count": 18200,
"is_parallel": true,
"self": 8.153882254006987,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.866839177999964,
"count": 18200,
"is_parallel": true,
"self": 4.866839177999964
},
"communicator.exchange": {
"total": 174.0902604229978,
"count": 18200,
"is_parallel": true,
"self": 174.0902604229978
},
"steps_from_proto": {
"total": 31.346021837994044,
"count": 18200,
"is_parallel": true,
"self": 6.368538867019254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.97748297097479,
"count": 182000,
"is_parallel": true,
"self": 24.97748297097479
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.729500003326393e-05,
"count": 1,
"self": 5.729500003326393e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 406.45848810602956,
"count": 334804,
"is_parallel": true,
"self": 8.90249506802212,
"children": {
"process_trajectory": {
"total": 233.57636181800717,
"count": 334804,
"is_parallel": true,
"self": 232.91012996100716,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6662318570000139,
"count": 4,
"is_parallel": true,
"self": 0.6662318570000139
}
}
},
"_update_policy": {
"total": 163.97963122000027,
"count": 90,
"is_parallel": true,
"self": 40.36756820600385,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.61206301399642,
"count": 4587,
"is_parallel": true,
"self": 123.61206301399642
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11691197700008615,
"count": 1,
"self": 0.0008195440001372845,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11609243299994887,
"count": 1,
"self": 0.11609243299994887
}
}
}
}
}
}
}