{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8564358353614807, "min": 0.8564358353614807, "max": 2.8531644344329834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8139.56591796875, "min": 8139.56591796875, "max": 29125.1015625, "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": 12.95347785949707, "min": 0.3176579177379608, "max": 12.95347785949707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2525.92822265625, "min": 61.62563705444336, "max": 2624.91845703125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07090882912983515, "min": 0.06176864563228675, "max": 0.07690817576321754, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2836353165193406, "min": 0.259700855151345, "max": 0.38454087881608773, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23230142241307333, "min": 0.11342478791416129, "max": 0.31041282415390015, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9292056896522933, "min": 0.45369915165664515, "max": 1.5134591255702223, "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": 25.204545454545453, "min": 3.3863636363636362, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 149.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 3.3863636363636362, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 149.0, "max": 1406.0, "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": "1759484687", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/chenyu/anaconda3/envs/hf-rl/bin/mlagents-learn ./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": "1759485256" }, "total": 568.9784714821726, "count": 1, "self": 0.4727358929812908, "children": { "run_training.setup": { "total": 0.020450767129659653, "count": 1, "self": 0.020450767129659653 }, "TrainerController.start_learning": { "total": 568.4852848220617, "count": 1, "self": 0.2555064493790269, "children": { "TrainerController._reset_env": { "total": 2.5859871124848723, "count": 1, "self": 2.5859871124848723 }, "TrainerController.advance": { "total": 565.5334436064586, "count": 18192, "self": 0.29400470294058323, "children": { "env_step": { "total": 426.53062696103007, "count": 18192, "self": 352.84131967276335, "children": { "SubprocessEnvManager._take_step": { "total": 73.53032399620861, "count": 18192, "self": 0.9845442194491625, "children": { "TorchPolicy.evaluate": { "total": 72.54577977675945, "count": 18192, "self": 72.54577977675945 } } }, "workers": { "total": 0.15898329205811024, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 567.1265360396355, "count": 18192, "is_parallel": true, "self": 241.8484125584364, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003405435010790825, "count": 1, "is_parallel": true, "self": 0.0009339367970824242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024714982137084007, "count": 10, "is_parallel": true, "self": 0.0024714982137084007 } } }, "UnityEnvironment.step": { "total": 0.03783043380826712, "count": 1, "is_parallel": true, "self": 0.0007311105728149414, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005852309986948967, "count": 1, "is_parallel": true, "self": 0.0005852309986948967 }, "communicator.exchange": { "total": 0.034000820480287075, "count": 1, "is_parallel": true, "self": 0.034000820480287075 }, "steps_from_proto": { "total": 0.0025132717564702034, "count": 1, "is_parallel": true, "self": 0.000550905242562294, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019623665139079094, "count": 10, "is_parallel": true, "self": 0.0019623665139079094 } } } } } } }, "UnityEnvironment.step": { "total": 325.27812348119915, "count": 18191, "is_parallel": true, "self": 12.847837121225893, "children": { "UnityEnvironment._generate_step_input": { "total": 7.931186631321907, "count": 18191, "is_parallel": true, "self": 7.931186631321907 }, "communicator.exchange": { "total": 260.7029867749661, "count": 18191, "is_parallel": true, "self": 260.7029867749661 }, "steps_from_proto": { "total": 43.796112953685224, "count": 18191, "is_parallel": true, "self": 9.185637504793704, "children": { "_process_rank_one_or_two_observation": { "total": 34.61047544889152, "count": 181910, "is_parallel": true, "self": 34.61047544889152 } } } } } } } } } } }, "trainer_advance": { "total": 138.70881194248796, "count": 18192, "self": 0.3086239118129015, "children": { "process_trajectory": { "total": 24.149280005134642, "count": 18192, "self": 23.803672161884606, "children": { "RLTrainer._checkpoint": { "total": 0.34560784325003624, "count": 4, "self": 0.34560784325003624 } } }, "_update_policy": { "total": 114.25090802554041, "count": 90, "self": 28.516322153620422, "children": { "TorchPPOOptimizer.update": { "total": 85.73458587191999, "count": 4587, "self": 85.73458587191999 } } } } } } }, "trainer_threads": { "total": 8.614733815193176e-07, "count": 1, "self": 8.614733815193176e-07 }, "TrainerController._save_models": { "total": 0.11034679226577282, "count": 1, "self": 0.0009701335802674294, "children": { "RLTrainer._checkpoint": { "total": 0.10937665868550539, "count": 1, "self": 0.10937665868550539 } } } } } } }