nossie0360's picture
First Push
fe193dc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8282950520515442,
"min": 0.8274566531181335,
"max": 2.8715152740478516,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7872.1162109375,
"min": 7872.1162109375,
"max": 29312.427734375,
"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": 12.99463939666748,
"min": 0.3769529163837433,
"max": 12.999096870422363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.95458984375,
"min": 73.12886810302734,
"max": 2651.815673828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06689798033867013,
"min": 0.06344719226648984,
"max": 0.07462044685862744,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2675919213546805,
"min": 0.2537887690659594,
"max": 0.36727401431748086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19981264063686716,
"min": 0.10748691069117437,
"max": 0.2846614657663832,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7992505625474686,
"min": 0.4299476427646975,
"max": 1.4233073288319158,
"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": 25.363636363636363,
"min": 2.9318181818181817,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 129.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 2.9318181818181817,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 129.0,
"max": 1394.0,
"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": "1741672151",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741672485"
},
"total": 333.7521186349986,
"count": 1,
"self": 0.22013430799779599,
"children": {
"run_training.setup": {
"total": 0.0181971860001795,
"count": 1,
"self": 0.0181971860001795
},
"TrainerController.start_learning": {
"total": 333.51378714100065,
"count": 1,
"self": 0.2912272398480127,
"children": {
"TrainerController._reset_env": {
"total": 2.1741058890002023,
"count": 1,
"self": 2.1741058890002023
},
"TrainerController.advance": {
"total": 330.99091958015197,
"count": 18192,
"self": 0.2288210702190554,
"children": {
"env_step": {
"total": 234.88804089298537,
"count": 18192,
"self": 160.61785864017838,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.08441073087852,
"count": 18192,
"self": 0.9125288057821308,
"children": {
"TorchPolicy.evaluate": {
"total": 73.17188192509639,
"count": 18192,
"self": 73.17188192509639
}
}
},
"workers": {
"total": 0.1857715219284728,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 332.68141578192626,
"count": 18192,
"is_parallel": true,
"self": 188.86434456589268,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002150516000256175,
"count": 1,
"is_parallel": true,
"self": 0.00124064700321469,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009098689970414853,
"count": 10,
"is_parallel": true,
"self": 0.0009098689970414853
}
}
},
"UnityEnvironment.step": {
"total": 0.01694619599948055,
"count": 1,
"is_parallel": true,
"self": 0.0001871820004453184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00014309599828266073,
"count": 1,
"is_parallel": true,
"self": 0.00014309599828266073
},
"communicator.exchange": {
"total": 0.016069998000602936,
"count": 1,
"is_parallel": true,
"self": 0.016069998000602936
},
"steps_from_proto": {
"total": 0.0005459200001496356,
"count": 1,
"is_parallel": true,
"self": 0.0001598130020283861,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003861069981212495,
"count": 10,
"is_parallel": true,
"self": 0.0003861069981212495
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 143.81707121603358,
"count": 18191,
"is_parallel": true,
"self": 3.25023041230088,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.854415935014913,
"count": 18191,
"is_parallel": true,
"self": 1.854415935014913
},
"communicator.exchange": {
"total": 129.6341209458842,
"count": 18191,
"is_parallel": true,
"self": 129.6341209458842
},
"steps_from_proto": {
"total": 9.078303922833584,
"count": 18191,
"is_parallel": true,
"self": 2.1011438461137004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.977160076719883,
"count": 181910,
"is_parallel": true,
"self": 6.977160076719883
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 95.87405761694754,
"count": 18192,
"self": 0.3468821040241892,
"children": {
"process_trajectory": {
"total": 20.381860238903755,
"count": 18192,
"self": 20.027073526900494,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3547867120032606,
"count": 4,
"self": 0.3547867120032606
}
}
},
"_update_policy": {
"total": 75.1453152740196,
"count": 90,
"self": 20.945438246993945,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.19987702702565,
"count": 4587,
"self": 54.19987702702565
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.630008672596887e-07,
"count": 1,
"self": 5.630008672596887e-07
},
"TrainerController._save_models": {
"total": 0.05753386899959878,
"count": 1,
"self": 0.0005629120005323784,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0569709569990664,
"count": 1,
"self": 0.0569709569990664
}
}
}
}
}
}
}