{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7923914790153503, "min": 0.7723963856697083, "max": 2.8145856857299805, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7530.888671875, "min": 7408.826171875, "max": 28731.291015625, "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": 13.354889869689941, "min": 0.36965304613113403, "max": 13.354889869689941, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2604.20361328125, "min": 71.71269226074219, "max": 2703.591796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0701138840765149, "min": 0.06408860788146471, "max": 0.0773161953953711, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2804555363060596, "min": 0.25635443152585885, "max": 0.3865809769768555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19938520254457698, "min": 0.1394660363119899, "max": 0.29035518946600897, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7975408101783079, "min": 0.5578641452479596, "max": 1.410598319535162, "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": 26.045454545454547, "min": 3.9318181818181817, "max": 26.70909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 173.0, "max": 1469.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.9318181818181817, "max": 26.70909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 173.0, "max": 1469.0, "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": "1781073282", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "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": "1781073775" }, "total": 492.55134698200004, "count": 1, "self": 0.5333216299998185, "children": { "run_training.setup": { "total": 0.022573102000023937, "count": 1, "self": 0.022573102000023937 }, "TrainerController.start_learning": { "total": 491.9954522500002, "count": 1, "self": 0.415551941001695, "children": { "TrainerController._reset_env": { "total": 3.423188868999887, "count": 1, "self": 3.423188868999887 }, "TrainerController.advance": { "total": 488.0722425879985, "count": 18192, "self": 0.45151646596832506, "children": { "env_step": { "total": 358.3259947370086, "count": 18192, "self": 279.2875344180459, "children": { "SubprocessEnvManager._take_step": { "total": 78.78214957995465, "count": 18192, "self": 1.4296126169595027, "children": { "TorchPolicy.evaluate": { "total": 77.35253696299515, "count": 18192, "self": 77.35253696299515 } } }, "workers": { "total": 0.2563107390080859, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 489.9754708300077, "count": 18192, "is_parallel": true, "self": 245.58902024097574, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005793071000198324, "count": 1, "is_parallel": true, "self": 0.003970647000414829, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018224239997834957, "count": 10, "is_parallel": true, "self": 0.0018224239997834957 } } }, "UnityEnvironment.step": { "total": 0.03804748499987909, "count": 1, "is_parallel": true, "self": 0.0006589460001578118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004531679999217886, "count": 1, "is_parallel": true, "self": 0.0004531679999217886 }, "communicator.exchange": { "total": 0.034942437999916365, "count": 1, "is_parallel": true, "self": 0.034942437999916365 }, "steps_from_proto": { "total": 0.0019929329998831236, "count": 1, "is_parallel": true, "self": 0.00040092599942909146, "children": { "_process_rank_one_or_two_observation": { "total": 0.001592007000454032, "count": 10, "is_parallel": true, "self": 0.001592007000454032 } } } } } } }, "UnityEnvironment.step": { "total": 244.38645058903194, "count": 18191, "is_parallel": true, "self": 10.983743151021372, "children": { "UnityEnvironment._generate_step_input": { "total": 6.0681068860033065, "count": 18191, "is_parallel": true, "self": 6.0681068860033065 }, "communicator.exchange": { "total": 186.44567714799996, "count": 18191, "is_parallel": true, "self": 186.44567714799996 }, "steps_from_proto": { "total": 40.8889234040073, "count": 18191, "is_parallel": true, "self": 7.395896302926758, "children": { "_process_rank_one_or_two_observation": { "total": 33.49302710108054, "count": 181910, "is_parallel": true, "self": 33.49302710108054 } } } } } } } } } } }, "trainer_advance": { "total": 129.29473138502158, "count": 18192, "self": 0.5400683339892112, "children": { "process_trajectory": { "total": 29.080675694032834, "count": 18192, "self": 28.63135377303297, "children": { "RLTrainer._checkpoint": { "total": 0.44932192099986423, "count": 4, "self": 0.44932192099986423 } } }, "_update_policy": { "total": 99.67398735699953, "count": 90, "self": 41.00865595699861, "children": { "TorchPPOOptimizer.update": { "total": 58.66533140000092, "count": 4587, "self": 58.66533140000092 } } } } } } }, "trainer_threads": { "total": 9.099999260797631e-07, "count": 1, "self": 9.099999260797631e-07 }, "TrainerController._save_models": { "total": 0.08446794200017393, "count": 1, "self": 0.0007689029998800834, "children": { "RLTrainer._checkpoint": { "total": 0.08369903900029385, "count": 1, "self": 0.08369903900029385 } } } } } } }