dhmeltzer's picture
first push
cf6c149
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0027345418930054,
"min": 1.0027345418930054,
"max": 2.870182991027832,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9574.109375,
"min": 9574.109375,
"max": 29393.54296875,
"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": 12.663389205932617,
"min": 0.37498313188552856,
"max": 12.663389205932617,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2469.36083984375,
"min": 72.7467269897461,
"max": 2560.03125,
"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": 0.0749770662217748,
"min": 0.06425611949200496,
"max": 0.0759091316877554,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2999082648870992,
"min": 0.25974969284303084,
"max": 0.37954565843877697,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19012556725419036,
"min": 0.12824285372306465,
"max": 0.30849646930308905,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7605022690167614,
"min": 0.5129714148922586,
"max": 1.5271859329705144,
"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": 25.09090909090909,
"min": 3.3181818181818183,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 146.0,
"max": 1363.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.3181818181818183,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 146.0,
"max": 1363.0,
"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": "1675220479",
"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": "1675220903"
},
"total": 424.633080829,
"count": 1,
"self": 0.393417204000059,
"children": {
"run_training.setup": {
"total": 0.10643192499998122,
"count": 1,
"self": 0.10643192499998122
},
"TrainerController.start_learning": {
"total": 424.13323169999995,
"count": 1,
"self": 0.5364616350040023,
"children": {
"TrainerController._reset_env": {
"total": 10.011396428000012,
"count": 1,
"self": 10.011396428000012
},
"TrainerController.advance": {
"total": 413.4675040239959,
"count": 18201,
"self": 0.2668057019889716,
"children": {
"env_step": {
"total": 413.20069832200693,
"count": 18201,
"self": 270.033773183009,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.90623383800022,
"count": 18201,
"self": 1.3740469819984469,
"children": {
"TorchPolicy.evaluate": {
"total": 141.53218685600177,
"count": 18201,
"self": 31.397400933998767,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.134785922003,
"count": 18201,
"self": 110.134785922003
}
}
}
}
},
"workers": {
"total": 0.26069130099773474,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 422.87924279299335,
"count": 18201,
"is_parallel": true,
"self": 204.15424841499072,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006394710999984454,
"count": 1,
"is_parallel": true,
"self": 0.003619931999992332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027747789999921224,
"count": 10,
"is_parallel": true,
"self": 0.0027747789999921224
}
}
},
"UnityEnvironment.step": {
"total": 0.041839873000014904,
"count": 1,
"is_parallel": true,
"self": 0.0004420430000209308,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002870029999826329,
"count": 1,
"is_parallel": true,
"self": 0.0002870029999826329
},
"communicator.exchange": {
"total": 0.03955997100001696,
"count": 1,
"is_parallel": true,
"self": 0.03955997100001696
},
"steps_from_proto": {
"total": 0.0015508559999943827,
"count": 1,
"is_parallel": true,
"self": 0.0003936180000323475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011572379999620352,
"count": 10,
"is_parallel": true,
"self": 0.0011572379999620352
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.72499437800263,
"count": 18200,
"is_parallel": true,
"self": 8.281530623001402,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.832303984000305,
"count": 18200,
"is_parallel": true,
"self": 4.832303984000305
},
"communicator.exchange": {
"total": 176.50613409401086,
"count": 18200,
"is_parallel": true,
"self": 176.50613409401086
},
"steps_from_proto": {
"total": 29.105025676990067,
"count": 18200,
"is_parallel": true,
"self": 6.256223153989026,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.84880252300104,
"count": 182000,
"is_parallel": true,
"self": 22.84880252300104
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.471700003705337e-05,
"count": 1,
"self": 4.471700003705337e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 410.5643409639738,
"count": 340408,
"is_parallel": true,
"self": 9.34739124696523,
"children": {
"process_trajectory": {
"total": 235.34688919200897,
"count": 340408,
"is_parallel": true,
"self": 234.64777399800897,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6991151940000009,
"count": 4,
"is_parallel": true,
"self": 0.6991151940000009
}
}
},
"_update_policy": {
"total": 165.8700605249996,
"count": 90,
"is_parallel": true,
"self": 41.61066486899597,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.25939565600362,
"count": 4587,
"is_parallel": true,
"self": 124.25939565600362
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1178248960000019,
"count": 1,
"self": 0.0009561839999605581,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11686871200004134,
"count": 1,
"self": 0.11686871200004134
}
}
}
}
}
}
}