{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9995168447494507, "min": 0.9576695561408997, "max": 2.8528950214385986, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9543.38671875, "min": 9543.38671875, "max": 29247.880859375, "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": 11.926902770996094, "min": 0.3564508855342865, "max": 11.926902770996094, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2325.74609375, "min": 69.15147399902344, "max": 2411.09326171875, "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": 23.318181818181817, "min": 3.772727272727273, "max": 23.381818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1026.0, "min": 166.0, "max": 1286.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.318181818181817, "min": 3.772727272727273, "max": 23.381818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1026.0, "min": 166.0, "max": 1286.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07213220873089476, "min": 0.06237596083220149, "max": 0.07341399442269475, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28852883492357906, "min": 0.24950384332880596, "max": 0.36331135333132214, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18396299759693005, "min": 0.12611652286175418, "max": 0.29359273517540857, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7358519903877202, "min": 0.5044660914470167, "max": 1.322461436484374, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029184900271699997, "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": 0.19728300000000004, "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": 0.0048644217, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "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": "1731439441", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731439990" }, "total": 548.5093360049999, "count": 1, "self": 0.5403197549999277, "children": { "run_training.setup": { "total": 0.06861640799999691, "count": 1, "self": 0.06861640799999691 }, "TrainerController.start_learning": { "total": 547.900399842, "count": 1, "self": 0.7456930250021969, "children": { "TrainerController._reset_env": { "total": 6.529666778999996, "count": 1, "self": 6.529666778999996 }, "TrainerController.advance": { "total": 540.5449566309978, "count": 18202, "self": 0.37117356399721757, "children": { "env_step": { "total": 540.1737830670006, "count": 18202, "self": 420.24005709700657, "children": { "SubprocessEnvManager._take_step": { "total": 119.54932209799753, "count": 18202, "self": 1.835999643998548, "children": { "TorchPolicy.evaluate": { "total": 117.71332245399898, "count": 18202, "self": 117.71332245399898 } } }, "workers": { "total": 0.38440387199651127, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 546.2707442190007, "count": 18202, "is_parallel": true, "self": 259.2466078979995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037018769999974666, "count": 1, "is_parallel": true, "self": 0.0009543959999689378, "children": { "_process_rank_one_or_two_observation": { "total": 0.002747481000028529, "count": 10, "is_parallel": true, "self": 0.002747481000028529 } } }, "UnityEnvironment.step": { "total": 0.04239649699999859, "count": 1, "is_parallel": true, "self": 0.0007851469999877736, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042579000000841916, "count": 1, "is_parallel": true, "self": 0.00042579000000841916 }, "communicator.exchange": { "total": 0.03860573200000772, "count": 1, "is_parallel": true, "self": 0.03860573200000772 }, "steps_from_proto": { "total": 0.002579827999994677, "count": 1, "is_parallel": true, "self": 0.00046555800000191994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021142699999927572, "count": 10, "is_parallel": true, "self": 0.0021142699999927572 } } } } } } }, "UnityEnvironment.step": { "total": 287.02413632100115, "count": 18201, "is_parallel": true, "self": 13.511846877993776, "children": { "UnityEnvironment._generate_step_input": { "total": 6.750068990009908, "count": 18201, "is_parallel": true, "self": 6.750068990009908 }, "communicator.exchange": { "total": 224.6687585789995, "count": 18201, "is_parallel": true, "self": 224.6687585789995 }, "steps_from_proto": { "total": 42.09346187399797, "count": 18201, "is_parallel": true, "self": 8.19308815898492, "children": { "_process_rank_one_or_two_observation": { "total": 33.900373715013046, "count": 182010, "is_parallel": true, "self": 33.900373715013046 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016973300000699965, "count": 1, "self": 0.00016973300000699965, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 534.6004403249945, "count": 711234, "is_parallel": true, "self": 15.03061006399821, "children": { "process_trajectory": { "total": 286.37337902299623, "count": 711234, "is_parallel": true, "self": 285.65528517699624, "children": { "RLTrainer._checkpoint": { "total": 0.7180938459999879, "count": 4, "is_parallel": true, "self": 0.7180938459999879 } } }, "_update_policy": { "total": 233.19645123800007, "count": 90, "is_parallel": true, "self": 70.21800834899724, "children": { "TorchPPOOptimizer.update": { "total": 162.97844288900282, "count": 4584, "is_parallel": true, "self": 162.97844288900282 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07991367399995397, "count": 1, "self": 0.0011739519999309778, "children": { "RLTrainer._checkpoint": { "total": 0.078739722000023, "count": 1, "self": 0.078739722000023 } } } } } } }