{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.776721239089966, "min": 2.776721239089966, "max": 2.875488519668579, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28589.123046875, "min": 28589.123046875, "max": 29352.986328125, "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": 1.347534418106079, "min": 0.34849560260772705, "max": 1.347534418106079, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 276.24456787109375, "min": 67.60814666748047, "max": 276.24456787109375, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07021250117378419, "min": 0.06445339168849208, "max": 0.07021250117378419, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35106250586892096, "min": 0.2578135667539683, "max": 0.35106250586892096, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2143111745516459, "min": 0.14448146721777305, "max": 0.2143111745516459, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0715558727582295, "min": 0.5779258688710922, "max": 1.0715558727582295, "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": 5.581818181818182, "min": 3.5681818181818183, "max": 5.581818181818182, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 307.0, "min": 157.0, "max": 307.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.581818181818182, "min": 3.5681818181818183, "max": 5.581818181818182, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 307.0, "min": 157.0, "max": 307.0, "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": "1747682404", "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": "1747682453" }, "total": 48.22458878799989, "count": 1, "self": 0.431276755999761, "children": { "run_training.setup": { "total": 0.03453125300006832, "count": 1, "self": 0.03453125300006832 }, "TrainerController.start_learning": { "total": 47.75878077900006, "count": 1, "self": 0.03711918000476544, "children": { "TrainerController._reset_env": { "total": 3.8994978370001263, "count": 1, "self": 3.8994978370001263 }, "TrainerController.advance": { "total": 43.658767740995245, "count": 1864, "self": 0.03822023099019134, "children": { "env_step": { "total": 31.085630769005093, "count": 1864, "self": 23.723120625011006, "children": { "SubprocessEnvManager._take_step": { "total": 7.341642006997063, "count": 1864, "self": 0.13246683699662753, "children": { "TorchPolicy.evaluate": { "total": 7.209175170000435, "count": 1864, "self": 7.209175170000435 } } }, "workers": { "total": 0.020868136997023612, "count": 1864, "self": 0.0, "children": { "worker_root": { "total": 47.32782412599886, "count": 1864, "is_parallel": true, "self": 26.510701796996955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006482291000111218, "count": 1, "is_parallel": true, "self": 0.004532377999794335, "children": { "_process_rank_one_or_two_observation": { "total": 0.001949913000316883, "count": 10, "is_parallel": true, "self": 0.001949913000316883 } } }, "UnityEnvironment.step": { "total": 0.03853112000001602, "count": 1, "is_parallel": true, "self": 0.0006478039997546148, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041499900021335634, "count": 1, "is_parallel": true, "self": 0.00041499900021335634 }, "communicator.exchange": { "total": 0.03539452299992263, "count": 1, "is_parallel": true, "self": 0.03539452299992263 }, "steps_from_proto": { "total": 0.0020737940001254174, "count": 1, "is_parallel": true, "self": 0.00044657499961431313, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016272190005111042, "count": 10, "is_parallel": true, "self": 0.0016272190005111042 } } } } } } }, "UnityEnvironment.step": { "total": 20.817122329001904, "count": 1863, "is_parallel": true, "self": 1.000447944000598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5775535669963574, "count": 1863, "is_parallel": true, "self": 0.5775535669963574 }, "communicator.exchange": { "total": 15.900597602000516, "count": 1863, "is_parallel": true, "self": 15.900597602000516 }, "steps_from_proto": { "total": 3.3385232160044325, "count": 1863, "is_parallel": true, "self": 0.5951375680003821, "children": { "_process_rank_one_or_two_observation": { "total": 2.7433856480040504, "count": 18630, "is_parallel": true, "self": 2.7433856480040504 } } } } } } } } } } }, "trainer_advance": { "total": 12.534916740999961, "count": 1864, "self": 0.04334248800273599, "children": { "process_trajectory": { "total": 2.832469748997255, "count": 1864, "self": 2.832469748997255 }, "_update_policy": { "total": 9.65910450399997, "count": 9, "self": 4.002077984001744, "children": { "TorchPPOOptimizer.update": { "total": 5.657026519998226, "count": 456, "self": 5.657026519998226 } } } } } } }, "trainer_threads": { "total": 9.129998943535611e-07, "count": 1, "self": 9.129998943535611e-07 }, "TrainerController._save_models": { "total": 0.16339510800003154, "count": 1, "self": 0.0008216619999075192, "children": { "RLTrainer._checkpoint": { "total": 0.16257344600012402, "count": 1, "self": 0.16257344600012402 } } } } } } }