Leonhard17's picture
First Push
eb4d8d7
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9290996789932251,
"min": 0.9290996789932251,
"max": 2.8594727516174316,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8871.0439453125,
"min": 8871.0439453125,
"max": 29566.947265625,
"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": 12.791175842285156,
"min": 0.4354913830757141,
"max": 12.791175842285156,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2494.279296875,
"min": 84.4853286743164,
"max": 2596.80908203125,
"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": 0.06859509986533535,
"min": 0.0601231886582408,
"max": 0.07591549995598981,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2743803994613414,
"min": 0.25584845095028297,
"max": 0.37478574371026996,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18897156212844102,
"min": 0.1287130056092899,
"max": 0.2813266641369053,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7558862485137641,
"min": 0.5148520224371596,
"max": 1.4066333206845265,
"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": 25.227272727272727,
"min": 3.9545454545454546,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 174.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.9545454545454546,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 174.0,
"max": 1376.0,
"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": "1677161990",
"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": "1.22.4",
"end_time_seconds": "1677162466"
},
"total": 476.4958960130001,
"count": 1,
"self": 0.39808808600002976,
"children": {
"run_training.setup": {
"total": 0.12042845999997098,
"count": 1,
"self": 0.12042845999997098
},
"TrainerController.start_learning": {
"total": 475.9773794670001,
"count": 1,
"self": 0.5621914949975917,
"children": {
"TrainerController._reset_env": {
"total": 9.745653032000064,
"count": 1,
"self": 9.745653032000064
},
"TrainerController.advance": {
"total": 465.5505759100024,
"count": 18203,
"self": 0.31268961500768455,
"children": {
"env_step": {
"total": 465.2378862949947,
"count": 18203,
"self": 319.06013910401873,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.89422559398452,
"count": 18203,
"self": 1.5537230359761907,
"children": {
"TorchPolicy.evaluate": {
"total": 144.34050255800832,
"count": 18203,
"self": 31.572941976003335,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.76756058200499,
"count": 18203,
"self": 112.76756058200499
}
}
}
}
},
"workers": {
"total": 0.28352159699147705,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.39230878801743,
"count": 18203,
"is_parallel": true,
"self": 230.63274342200702,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007469276999927388,
"count": 1,
"is_parallel": true,
"self": 0.003794728999992003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036745479999353847,
"count": 10,
"is_parallel": true,
"self": 0.0036745479999353847
}
}
},
"UnityEnvironment.step": {
"total": 0.05537766700001612,
"count": 1,
"is_parallel": true,
"self": 0.000627435000069454,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004000220000079935,
"count": 1,
"is_parallel": true,
"self": 0.0004000220000079935
},
"communicator.exchange": {
"total": 0.05240477600000304,
"count": 1,
"is_parallel": true,
"self": 0.05240477600000304
},
"steps_from_proto": {
"total": 0.0019454339999356307,
"count": 1,
"is_parallel": true,
"self": 0.00043376400003580784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015116699998998229,
"count": 10,
"is_parallel": true,
"self": 0.0015116699998998229
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.7595653660104,
"count": 18202,
"is_parallel": true,
"self": 9.936295509014144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.529388699989909,
"count": 18202,
"is_parallel": true,
"self": 5.529388699989909
},
"communicator.exchange": {
"total": 195.43787127499593,
"count": 18202,
"is_parallel": true,
"self": 195.43787127499593
},
"steps_from_proto": {
"total": 32.856009882010426,
"count": 18202,
"is_parallel": true,
"self": 7.337099830001989,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.518910052008437,
"count": 182020,
"is_parallel": true,
"self": 25.518910052008437
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012190000006739865,
"count": 1,
"self": 0.00012190000006739865,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 461.98251544400114,
"count": 408642,
"is_parallel": true,
"self": 10.624215969942725,
"children": {
"process_trajectory": {
"total": 264.608070235058,
"count": 408642,
"is_parallel": true,
"self": 263.75040241405793,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8576678210000637,
"count": 4,
"is_parallel": true,
"self": 0.8576678210000637
}
}
},
"_update_policy": {
"total": 186.75022923900042,
"count": 90,
"is_parallel": true,
"self": 63.372033114994224,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.3781961240062,
"count": 4587,
"is_parallel": true,
"self": 123.3781961240062
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11883712999997442,
"count": 1,
"self": 0.0009154150000085792,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11792171499996584,
"count": 1,
"self": 0.11792171499996584
}
}
}
}
}
}
}