Augpiano's picture
First Push
06f2621 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8833295702934265,
"min": 0.8833295702934265,
"max": 2.8413403034210205,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8395.1640625,
"min": 8395.1640625,
"max": 29004.40234375,
"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": 12.831097602844238,
"min": 0.44762498140335083,
"max": 12.831097602844238,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2502.06396484375,
"min": 86.83924865722656,
"max": 2617.048828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07378984421409447,
"min": 0.06280932114122884,
"max": 0.07548933332941041,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2951593768563779,
"min": 0.25239423615001966,
"max": 0.37348387772148917,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2109374662532526,
"min": 0.13215661485332486,
"max": 0.28635984673803927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8437498650130104,
"min": 0.5286264594132994,
"max": 1.37880194420908,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.886363636363637,
"min": 3.6818181818181817,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 162.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.6818181818181817,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 162.0,
"max": 1398.0,
"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": "1764851642",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764852196"
},
"total": 554.2207569479999,
"count": 1,
"self": 0.5430039230000148,
"children": {
"run_training.setup": {
"total": 0.033131314999991446,
"count": 1,
"self": 0.033131314999991446
},
"TrainerController.start_learning": {
"total": 553.6446217099999,
"count": 1,
"self": 0.5895426850061085,
"children": {
"TrainerController._reset_env": {
"total": 3.323235618999888,
"count": 1,
"self": 3.323235618999888
},
"TrainerController.advance": {
"total": 549.6657114209941,
"count": 18192,
"self": 0.6501894449900192,
"children": {
"env_step": {
"total": 398.0494710240064,
"count": 18192,
"self": 345.18316477101394,
"children": {
"SubprocessEnvManager._take_step": {
"total": 52.50136397700385,
"count": 18192,
"self": 1.8538022610080134,
"children": {
"TorchPolicy.evaluate": {
"total": 50.647561715995835,
"count": 18192,
"self": 50.647561715995835
}
}
},
"workers": {
"total": 0.3649422759885965,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 550.982588508982,
"count": 18192,
"is_parallel": true,
"self": 252.11939339398054,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003662898000129644,
"count": 1,
"is_parallel": true,
"self": 0.0020040580002387287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016588399998909154,
"count": 10,
"is_parallel": true,
"self": 0.0016588399998909154
}
}
},
"UnityEnvironment.step": {
"total": 0.048045665000017834,
"count": 1,
"is_parallel": true,
"self": 0.0007791729999553354,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005569799998283997,
"count": 1,
"is_parallel": true,
"self": 0.0005569799998283997
},
"communicator.exchange": {
"total": 0.04381720300011693,
"count": 1,
"is_parallel": true,
"self": 0.04381720300011693
},
"steps_from_proto": {
"total": 0.002892309000117166,
"count": 1,
"is_parallel": true,
"self": 0.0004366980001577758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00245561099995939,
"count": 10,
"is_parallel": true,
"self": 0.00245561099995939
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 298.8631951150014,
"count": 18191,
"is_parallel": true,
"self": 14.1143021920318,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.417207657980271,
"count": 18191,
"is_parallel": true,
"self": 7.417207657980271
},
"communicator.exchange": {
"total": 229.99019347399076,
"count": 18191,
"is_parallel": true,
"self": 229.99019347399076
},
"steps_from_proto": {
"total": 47.34149179099859,
"count": 18191,
"is_parallel": true,
"self": 8.35161265404031,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.98987913695828,
"count": 181910,
"is_parallel": true,
"self": 38.98987913695828
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 150.96605095199766,
"count": 18192,
"self": 0.7488629460040102,
"children": {
"process_trajectory": {
"total": 28.267118170993854,
"count": 18192,
"self": 27.907027715993763,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3600904550000905,
"count": 4,
"self": 0.3600904550000905
}
}
},
"_update_policy": {
"total": 121.9500698349998,
"count": 90,
"self": 46.700781013994174,
"children": {
"TorchPPOOptimizer.update": {
"total": 75.24928882100562,
"count": 4587,
"self": 75.24928882100562
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0940000265691197e-06,
"count": 1,
"self": 1.0940000265691197e-06
},
"TrainerController._save_models": {
"total": 0.06613089099982972,
"count": 1,
"self": 0.0009496819998275896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06518120900000213,
"count": 1,
"self": 0.06518120900000213
}
}
}
}
}
}
}