{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.799094021320343, "min": 0.799094021320343, "max": 2.855692148208618, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7594.58984375, "min": 7594.58984375, "max": 29150.90625, "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": 13.11205005645752, "min": 0.45003965497016907, "max": 13.11917781829834, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2556.849853515625, "min": 87.30769348144531, "max": 2680.13623046875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07121148213513614, "min": 0.06236260744249996, "max": 0.0765884007188088, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2848459285405446, "min": 0.2611954822535992, "max": 0.3669093503047799, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19758896650198626, "min": 0.11853612251191711, "max": 0.2644106449157584, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.790355866007945, "min": 0.47414449004766845, "max": 1.2676674545395608, "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": 25.772727272727273, "min": 3.75, "max": 26.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 165.0, "max": 1443.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.75, "max": 26.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 165.0, "max": 1443.0, "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": "1753752091", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753752654" }, "total": 563.0226095069997, "count": 1, "self": 0.5533200189997842, "children": { "run_training.setup": { "total": 0.04412942499993733, "count": 1, "self": 0.04412942499993733 }, "TrainerController.start_learning": { "total": 562.425160063, "count": 1, "self": 0.6026152830318097, "children": { "TrainerController._reset_env": { "total": 4.58267774099977, "count": 1, "self": 4.58267774099977 }, "TrainerController.advance": { "total": 557.163535324968, "count": 18192, "self": 0.7266329789190422, "children": { "env_step": { "total": 396.2885127350046, "count": 18192, "self": 339.7174967910132, "children": { "SubprocessEnvManager._take_step": { "total": 56.19642859897385, "count": 18192, "self": 2.052826371986157, "children": { "TorchPolicy.evaluate": { "total": 54.143602226987696, "count": 18192, "self": 54.143602226987696 } } }, "workers": { "total": 0.3745873450175168, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 560.0572945720182, "count": 18192, "is_parallel": true, "self": 266.48354166908575, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007592401000238169, "count": 1, "is_parallel": true, "self": 0.004702240001279279, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028901609989588906, "count": 10, "is_parallel": true, "self": 0.0028901609989588906 } } }, "UnityEnvironment.step": { "total": 0.045126428000003216, "count": 1, "is_parallel": true, "self": 0.0007104149999577203, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000480879999940953, "count": 1, "is_parallel": true, "self": 0.000480879999940953 }, "communicator.exchange": { "total": 0.041517481000028056, "count": 1, "is_parallel": true, "self": 0.041517481000028056 }, "steps_from_proto": { "total": 0.0024176520000764867, "count": 1, "is_parallel": true, "self": 0.00047193799991873675, "children": { "_process_rank_one_or_two_observation": { "total": 0.00194571400015775, "count": 10, "is_parallel": true, "self": 0.00194571400015775 } } } } } } }, "UnityEnvironment.step": { "total": 293.5737529029325, "count": 18191, "is_parallel": true, "self": 14.026303270972221, "children": { "UnityEnvironment._generate_step_input": { "total": 7.730564928018794, "count": 18191, "is_parallel": true, "self": 7.730564928018794 }, "communicator.exchange": { "total": 230.16987558097117, "count": 18191, "is_parallel": true, "self": 230.16987558097117 }, "steps_from_proto": { "total": 41.6470091229703, "count": 18191, "is_parallel": true, "self": 8.277735337957438, "children": { "_process_rank_one_or_two_observation": { "total": 33.369273785012865, "count": 181910, "is_parallel": true, "self": 33.369273785012865 } } } } } } } } } } }, "trainer_advance": { "total": 160.14838961104442, "count": 18192, "self": 0.8112371740539857, "children": { "process_trajectory": { "total": 31.358220026989784, "count": 18192, "self": 30.83302540998966, "children": { "RLTrainer._checkpoint": { "total": 0.5251946170001247, "count": 4, "self": 0.5251946170001247 } } }, "_update_policy": { "total": 127.97893241000065, "count": 90, "self": 49.240343202999156, "children": { "TorchPPOOptimizer.update": { "total": 78.7385892070015, "count": 4587, "self": 78.7385892070015 } } } } } } }, "trainer_threads": { "total": 1.0780004231492057e-06, "count": 1, "self": 1.0780004231492057e-06 }, "TrainerController._save_models": { "total": 0.07633063599996603, "count": 1, "self": 0.0011246979997849849, "children": { "RLTrainer._checkpoint": { "total": 0.07520593800018105, "count": 1, "self": 0.07520593800018105 } } } } } } }