{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9171742796897888, "min": 0.9006611108779907, "max": 2.8495240211486816, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8716.82421875, "min": 8716.82421875, "max": 29087.94140625, "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": 12.195295333862305, "min": 0.18924090266227722, "max": 12.195295333862305, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2378.08251953125, "min": 36.71273422241211, "max": 2477.81005859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06189574459402174, "min": 0.06125764620773422, "max": 0.07721048797499022, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24758297837608695, "min": 0.24758297837608695, "max": 0.38605243987495114, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17751969926643607, "min": 0.11261443911444433, "max": 0.32233243935248435, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7100787970657443, "min": 0.4504577564577773, "max": 1.6116621967624216, "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": 24.386363636363637, "min": 3.477272727272727, "max": 24.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1073.0, "min": 153.0, "max": 1303.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.386363636363637, "min": 3.477272727272727, "max": 24.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1073.0, "min": 153.0, "max": 1303.0, "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": "1777402317", "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": "1777402806" }, "total": 489.0206003049999, "count": 1, "self": 0.4324473859998079, "children": { "run_training.setup": { "total": 0.026586395000094853, "count": 1, "self": 0.026586395000094853 }, "TrainerController.start_learning": { "total": 488.561566524, "count": 1, "self": 0.3822858839998844, "children": { "TrainerController._reset_env": { "total": 2.8800389440000345, "count": 1, "self": 2.8800389440000345 }, "TrainerController.advance": { "total": 485.2173958770004, "count": 18192, "self": 0.4167344830248112, "children": { "env_step": { "total": 356.9214911289831, "count": 18192, "self": 279.5249109559928, "children": { "SubprocessEnvManager._take_step": { "total": 77.16068992699672, "count": 18192, "self": 1.3836612630173022, "children": { "TorchPolicy.evaluate": { "total": 75.77702866397942, "count": 18192, "self": 75.77702866397942 } } }, "workers": { "total": 0.23589024599357344, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 486.4222676879947, "count": 18192, "is_parallel": true, "self": 240.48502267498498, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004590696000036587, "count": 1, "is_parallel": true, "self": 0.0030182669999021527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015724290001344343, "count": 10, "is_parallel": true, "self": 0.0015724290001344343 } } }, "UnityEnvironment.step": { "total": 0.03819250499998361, "count": 1, "is_parallel": true, "self": 0.0006462499999315696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041047600007004803, "count": 1, "is_parallel": true, "self": 0.00041047600007004803 }, "communicator.exchange": { "total": 0.03523925499996494, "count": 1, "is_parallel": true, "self": 0.03523925499996494 }, "steps_from_proto": { "total": 0.0018965240000170525, "count": 1, "is_parallel": true, "self": 0.000373931999774868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015225920002421844, "count": 10, "is_parallel": true, "self": 0.0015225920002421844 } } } } } } }, "UnityEnvironment.step": { "total": 245.93724501300971, "count": 18191, "is_parallel": true, "self": 11.285879708036532, "children": { "UnityEnvironment._generate_step_input": { "total": 6.037403234979024, "count": 18191, "is_parallel": true, "self": 6.037403234979024 }, "communicator.exchange": { "total": 186.5987913809962, "count": 18191, "is_parallel": true, "self": 186.5987913809962 }, "steps_from_proto": { "total": 42.015170688997955, "count": 18191, "is_parallel": true, "self": 7.065581430994484, "children": { "_process_rank_one_or_two_observation": { "total": 34.94958925800347, "count": 181910, "is_parallel": true, "self": 34.94958925800347 } } } } } } } } } } }, "trainer_advance": { "total": 127.87917026499247, "count": 18192, "self": 0.4818571119749322, "children": { "process_trajectory": { "total": 29.308211688016513, "count": 18192, "self": 28.885702216016398, "children": { "RLTrainer._checkpoint": { "total": 0.42250947200011524, "count": 4, "self": 0.42250947200011524 } } }, "_update_policy": { "total": 98.08910146500102, "count": 90, "self": 40.2420132530026, "children": { "TorchPPOOptimizer.update": { "total": 57.847088211998425, "count": 4587, "self": 57.847088211998425 } } } } } } }, "trainer_threads": { "total": 1.1499998890940333e-06, "count": 1, "self": 1.1499998890940333e-06 }, "TrainerController._save_models": { "total": 0.0818446689997927, "count": 1, "self": 0.0007162599997627694, "children": { "RLTrainer._checkpoint": { "total": 0.08112840900002993, "count": 1, "self": 0.08112840900002993 } } } } } } }