{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9867058396339417, "min": 0.9867058396339417, "max": 2.855360984802246, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9377.65234375, "min": 9377.65234375, "max": 29147.525390625, "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": 11.593358993530273, "min": 0.4048781394958496, "max": 11.593358993530273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2260.705078125, "min": 78.54635620117188, "max": 2339.66845703125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06805095454275907, "min": 0.06101754219355594, "max": 0.07939745701379233, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2722038181710363, "min": 0.24407016877422377, "max": 0.3655686573286349, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20956417231583127, "min": 0.14035315634500162, "max": 0.2780855547563702, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8382566892633251, "min": 0.5614126253800065, "max": 1.3904277737818511, "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": 23.068181818181817, "min": 3.9318181818181817, "max": 23.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1015.0, "min": 173.0, "max": 1247.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.068181818181817, "min": 3.9318181818181817, "max": 23.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1015.0, "min": 173.0, "max": 1247.0, "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": "1754732964", "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 --force", "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": "1754733425" }, "total": 460.38618593699994, "count": 1, "self": 0.4422862030003216, "children": { "run_training.setup": { "total": 0.021629950999795255, "count": 1, "self": 0.021629950999795255 }, "TrainerController.start_learning": { "total": 459.9222697829998, "count": 1, "self": 0.4251238790188836, "children": { "TrainerController._reset_env": { "total": 2.8040456639998865, "count": 1, "self": 2.8040456639998865 }, "TrainerController.advance": { "total": 456.60348105798084, "count": 18192, "self": 0.4337265660187768, "children": { "env_step": { "total": 332.24485932098605, "count": 18192, "self": 255.50818114395952, "children": { "SubprocessEnvManager._take_step": { "total": 76.47890752100284, "count": 18192, "self": 1.3712466240135655, "children": { "TorchPolicy.evaluate": { "total": 75.10766089698927, "count": 18192, "self": 75.10766089698927 } } }, "workers": { "total": 0.25777065602369476, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 458.28200890900007, "count": 18192, "is_parallel": true, "self": 234.44952990504885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005899421999856713, "count": 1, "is_parallel": true, "self": 0.004424037999569919, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014753840002867946, "count": 10, "is_parallel": true, "self": 0.0014753840002867946 } } }, "UnityEnvironment.step": { "total": 0.037125285000001895, "count": 1, "is_parallel": true, "self": 0.0005632660001992917, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044404899995242886, "count": 1, "is_parallel": true, "self": 0.00044404899995242886 }, "communicator.exchange": { "total": 0.033270511999944574, "count": 1, "is_parallel": true, "self": 0.033270511999944574 }, "steps_from_proto": { "total": 0.0028474579999056004, "count": 1, "is_parallel": true, "self": 0.00041562699971109396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024318310001945065, "count": 10, "is_parallel": true, "self": 0.0024318310001945065 } } } } } } }, "UnityEnvironment.step": { "total": 223.83247900395122, "count": 18191, "is_parallel": true, "self": 10.136517876984499, "children": { "UnityEnvironment._generate_step_input": { "total": 5.817597737956021, "count": 18191, "is_parallel": true, "self": 5.817597737956021 }, "communicator.exchange": { "total": 174.1709923170033, "count": 18191, "is_parallel": true, "self": 174.1709923170033 }, "steps_from_proto": { "total": 33.70737107200739, "count": 18191, "is_parallel": true, "self": 6.092054631999872, "children": { "_process_rank_one_or_two_observation": { "total": 27.61531644000752, "count": 181910, "is_parallel": true, "self": 27.61531644000752 } } } } } } } } } } }, "trainer_advance": { "total": 123.92489517097601, "count": 18192, "self": 0.53594479897788, "children": { "process_trajectory": { "total": 28.125797378997504, "count": 18192, "self": 27.684720138997363, "children": { "RLTrainer._checkpoint": { "total": 0.4410772400001406, "count": 4, "self": 0.4410772400001406 } } }, "_update_policy": { "total": 95.26315299300063, "count": 90, "self": 38.486975856991194, "children": { "TorchPPOOptimizer.update": { "total": 56.77617713600944, "count": 4587, "self": 56.77617713600944 } } } } } } }, "trainer_threads": { "total": 1.0680000741558615e-06, "count": 1, "self": 1.0680000741558615e-06 }, "TrainerController._save_models": { "total": 0.08961811400013175, "count": 1, "self": 0.0009565830000610731, "children": { "RLTrainer._checkpoint": { "total": 0.08866153100007068, "count": 1, "self": 0.08866153100007068 } } } } } } }