mdapri's picture
copied almost entirey
70162ea
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8301334381103516,
"min": 0.8301334381103516,
"max": 2.8570845127105713,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7926.1142578125,
"min": 7926.1142578125,
"max": 29259.40234375,
"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": 12.669025421142578,
"min": 0.3926461637020111,
"max": 12.669025421142578,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2470.4599609375,
"min": 76.17335510253906,
"max": 2559.474853515625,
"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": 0.07381086254848496,
"min": 0.05976772057068707,
"max": 0.07800054616539046,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2952434501939398,
"min": 0.23907088228274828,
"max": 0.38602538797296765,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2102540106165643,
"min": 0.1224503794915554,
"max": 0.29603951475491713,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8410160424662572,
"min": 0.4898015179662216,
"max": 1.3974091977465388,
"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": 3.6363636363636362,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 160.0,
"max": 1363.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.6363636363636362,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 160.0,
"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": "1677410548",
"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": "1677410997"
},
"total": 449.4359973379999,
"count": 1,
"self": 0.4330329209997217,
"children": {
"run_training.setup": {
"total": 0.12183342399998764,
"count": 1,
"self": 0.12183342399998764
},
"TrainerController.start_learning": {
"total": 448.88113099300017,
"count": 1,
"self": 0.5364385040313664,
"children": {
"TrainerController._reset_env": {
"total": 8.919209450999915,
"count": 1,
"self": 8.919209450999915
},
"TrainerController.advance": {
"total": 439.30910648796885,
"count": 18202,
"self": 0.27223242696391026,
"children": {
"env_step": {
"total": 439.03687406100494,
"count": 18202,
"self": 301.66228375501214,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.10912443399798,
"count": 18202,
"self": 1.4735211160004837,
"children": {
"TorchPolicy.evaluate": {
"total": 135.6356033179975,
"count": 18202,
"self": 30.355325123000284,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.28027819499721,
"count": 18202,
"self": 105.28027819499721
}
}
}
}
},
"workers": {
"total": 0.2654658719948202,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 447.4036147750012,
"count": 18202,
"is_parallel": true,
"self": 214.82048519200362,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007280225999920731,
"count": 1,
"is_parallel": true,
"self": 0.00549329499972373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017869310001970007,
"count": 10,
"is_parallel": true,
"self": 0.0017869310001970007
}
}
},
"UnityEnvironment.step": {
"total": 0.034462489999896206,
"count": 1,
"is_parallel": true,
"self": 0.0005540099998597725,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000414322000096945,
"count": 1,
"is_parallel": true,
"self": 0.000414322000096945
},
"communicator.exchange": {
"total": 0.031712986000002275,
"count": 1,
"is_parallel": true,
"self": 0.031712986000002275
},
"steps_from_proto": {
"total": 0.0017811719999372144,
"count": 1,
"is_parallel": true,
"self": 0.00042455199968571833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001356620000251496,
"count": 10,
"is_parallel": true,
"self": 0.001356620000251496
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.58312958299757,
"count": 18201,
"is_parallel": true,
"self": 9.308956588043202,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.098076326987666,
"count": 18201,
"is_parallel": true,
"self": 5.098076326987666
},
"communicator.exchange": {
"total": 187.8107374069848,
"count": 18201,
"is_parallel": true,
"self": 187.8107374069848
},
"steps_from_proto": {
"total": 30.365359260981904,
"count": 18201,
"is_parallel": true,
"self": 6.557378190000691,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.807981070981214,
"count": 182010,
"is_parallel": true,
"self": 23.807981070981214
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015198599999166618,
"count": 1,
"self": 0.00015198599999166618,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 436.0812312270573,
"count": 398058,
"is_parallel": true,
"self": 9.693759319111678,
"children": {
"process_trajectory": {
"total": 250.34198347594588,
"count": 398058,
"is_parallel": true,
"self": 249.63186463994566,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7101188360002197,
"count": 4,
"is_parallel": true,
"self": 0.7101188360002197
}
}
},
"_update_policy": {
"total": 176.04548843199973,
"count": 90,
"is_parallel": true,
"self": 59.965546080006334,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.0799423519934,
"count": 4587,
"is_parallel": true,
"self": 116.0799423519934
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11622456400004921,
"count": 1,
"self": 0.0008664950000820681,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11535806899996714,
"count": 1,
"self": 0.11535806899996714
}
}
}
}
}
}
}