Joshhhhhhhhhh's picture
First Push
49f3027 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.6384027004241943,
"min": 2.6384027004241943,
"max": 2.816310167312622,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 27164.994140625,
"min": 27164.994140625,
"max": 28748.89453125,
"count": 2
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 9952.0,
"max": 19992.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.2819966077804565,
"min": 0.43862345814704895,
"max": 1.2819966077804565,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 262.8092956542969,
"min": 85.09294891357422,
"max": 262.8092956542969,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0657108345110079,
"min": 0.0657108345110079,
"max": 0.07355986719696875,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3285541725550395,
"min": 0.294239468787875,
"max": 0.3285541725550395,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19006702070142711,
"min": 0.11448344941177936,
"max": 0.19006702070142711,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9503351035071356,
"min": 0.45793379764711745,
"max": 0.9503351035071356,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032007656e-05,
"min": 7.032007656e-05,
"max": 0.00021882002706000002,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0003516003828,
"min": 0.0003516003828,
"max": 0.0008752801082400001,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.12344000000000002,
"min": 0.12344000000000002,
"max": 0.17294,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.6172000000000001,
"min": 0.6172000000000001,
"max": 0.69176,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0011796560000000003,
"min": 0.0011796560000000003,
"max": 0.003649706,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.005898280000000001,
"min": 0.005898280000000001,
"max": 0.014598824,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.254545454545455,
"min": 3.1818181818181817,
"max": 5.254545454545455,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 289.0,
"min": 140.0,
"max": 289.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.254545454545455,
"min": 3.1818181818181817,
"max": 5.254545454545455,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 289.0,
"min": 140.0,
"max": 289.0,
"count": 2
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1748498383",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748498432"
},
"total": 48.70514106600001,
"count": 1,
"self": 0.4333062590000054,
"children": {
"run_training.setup": {
"total": 0.02255363300002955,
"count": 1,
"self": 0.02255363300002955
},
"TrainerController.start_learning": {
"total": 48.249281173999975,
"count": 1,
"self": 0.03802773700340367,
"children": {
"TrainerController._reset_env": {
"total": 3.167170128999942,
"count": 1,
"self": 3.167170128999942
},
"TrainerController.advance": {
"total": 44.896046865996595,
"count": 1864,
"self": 0.04116445899614973,
"children": {
"env_step": {
"total": 32.34826990400086,
"count": 1864,
"self": 24.69948175800164,
"children": {
"SubprocessEnvManager._take_step": {
"total": 7.627801059998092,
"count": 1864,
"self": 0.1336733280000999,
"children": {
"TorchPolicy.evaluate": {
"total": 7.494127731997992,
"count": 1864,
"self": 7.494127731997992
}
}
},
"workers": {
"total": 0.020987086001127864,
"count": 1864,
"self": 0.0,
"children": {
"worker_root": {
"total": 47.82055500699846,
"count": 1864,
"is_parallel": true,
"self": 26.19447967900021,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.015488933000028737,
"count": 1,
"is_parallel": true,
"self": 0.014097184000206653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013917489998220844,
"count": 10,
"is_parallel": true,
"self": 0.0013917489998220844
}
}
},
"UnityEnvironment.step": {
"total": 0.0364610490000814,
"count": 1,
"is_parallel": true,
"self": 0.0006784939999988637,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043809300007069396,
"count": 1,
"is_parallel": true,
"self": 0.00043809300007069396
},
"communicator.exchange": {
"total": 0.03307848700001159,
"count": 1,
"is_parallel": true,
"self": 0.03307848700001159
},
"steps_from_proto": {
"total": 0.002265975000000253,
"count": 1,
"is_parallel": true,
"self": 0.0004023720001669062,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001863602999833347,
"count": 10,
"is_parallel": true,
"self": 0.001863602999833347
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 21.62607532799825,
"count": 1863,
"is_parallel": true,
"self": 0.998653592997357,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.564042701001199,
"count": 1863,
"is_parallel": true,
"self": 0.564042701001199
},
"communicator.exchange": {
"total": 16.75182077899899,
"count": 1863,
"is_parallel": true,
"self": 16.75182077899899
},
"steps_from_proto": {
"total": 3.3115582550007048,
"count": 1863,
"is_parallel": true,
"self": 0.5953660939948122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.7161921610058926,
"count": 18630,
"is_parallel": true,
"self": 2.7161921610058926
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 12.506612502999587,
"count": 1864,
"self": 0.0460108250013036,
"children": {
"process_trajectory": {
"total": 2.913369232998434,
"count": 1864,
"self": 2.913369232998434
},
"_update_policy": {
"total": 9.54723244499985,
"count": 9,
"self": 3.945371630001773,
"children": {
"TorchPPOOptimizer.update": {
"total": 5.601860814998076,
"count": 456,
"self": 5.601860814998076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.590000106778461e-07,
"count": 1,
"self": 8.590000106778461e-07
},
"TrainerController._save_models": {
"total": 0.1480355830000235,
"count": 1,
"self": 0.0007859960001042055,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1472495869999193,
"count": 1,
"self": 0.1472495869999193
}
}
}
}
}
}
}