{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8317452073097229, "min": 0.8317452073097229, "max": 2.86214280128479, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7904.90625, "min": 7904.90625, "max": 29216.75390625, "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": 12.87293815612793, "min": 0.3050481975078583, "max": 12.87293815612793, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.222900390625, "min": 59.17934799194336, "max": 2601.0673828125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07268064973890004, "min": 0.06214246416807417, "max": 0.07867881900011864, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29072259895560015, "min": 0.24856985667229667, "max": 0.3725369908677428, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1921825854874709, "min": 0.12688603054038158, "max": 0.30848638310151943, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7687303419498837, "min": 0.5075441221615263, "max": 1.5424319155075972, "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": 25.75, "min": 3.590909090909091, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 158.0, "max": 1385.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.590909090909091, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 158.0, "max": 1385.0, "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": "1739107943", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739108370" }, "total": 427.5024893069999, "count": 1, "self": 0.4380111699997542, "children": { "run_training.setup": { "total": 0.021245147000172437, "count": 1, "self": 0.021245147000172437 }, "TrainerController.start_learning": { "total": 427.04323299, "count": 1, "self": 0.34450161702488913, "children": { "TrainerController._reset_env": { "total": 2.233746338000401, "count": 1, "self": 2.233746338000401 }, "TrainerController.advance": { "total": 424.37310269597447, "count": 18192, "self": 0.36735161699198216, "children": { "env_step": { "total": 298.66908398901614, "count": 18192, "self": 227.55397627603315, "children": { "SubprocessEnvManager._take_step": { "total": 70.90680342899259, "count": 18192, "self": 1.2187335560574866, "children": { "TorchPolicy.evaluate": { "total": 69.6880698729351, "count": 18192, "self": 69.6880698729351 } } }, "workers": { "total": 0.20830428399040102, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 425.45446078197665, "count": 18192, "is_parallel": true, "self": 225.87444271795857, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021840249996785133, "count": 1, "is_parallel": true, "self": 0.0006801879990234738, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015038370006550394, "count": 10, "is_parallel": true, "self": 0.0015038370006550394 } } }, "UnityEnvironment.step": { "total": 0.06548560800001724, "count": 1, "is_parallel": true, "self": 0.0005569240001932485, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003473779997875681, "count": 1, "is_parallel": true, "self": 0.0003473779997875681 }, "communicator.exchange": { "total": 0.06272946099988985, "count": 1, "is_parallel": true, "self": 0.06272946099988985 }, "steps_from_proto": { "total": 0.001851845000146568, "count": 1, "is_parallel": true, "self": 0.0003541890005180903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014976559996284777, "count": 10, "is_parallel": true, "self": 0.0014976559996284777 } } } } } } }, "UnityEnvironment.step": { "total": 199.58001806401808, "count": 18191, "is_parallel": true, "self": 9.514904223998656, "children": { "UnityEnvironment._generate_step_input": { "total": 5.287402872990242, "count": 18191, "is_parallel": true, "self": 5.287402872990242 }, "communicator.exchange": { "total": 154.53151239704312, "count": 18191, "is_parallel": true, "self": 154.53151239704312 }, "steps_from_proto": { "total": 30.246198569986063, "count": 18191, "is_parallel": true, "self": 5.332871644017814, "children": { "_process_rank_one_or_two_observation": { "total": 24.91332692596825, "count": 181910, "is_parallel": true, "self": 24.91332692596825 } } } } } } } } } } }, "trainer_advance": { "total": 125.33666708996634, "count": 18192, "self": 0.40465278698684415, "children": { "process_trajectory": { "total": 26.82514596097826, "count": 18192, "self": 26.23723380197862, "children": { "RLTrainer._checkpoint": { "total": 0.587912158999643, "count": 4, "self": 0.587912158999643 } } }, "_update_policy": { "total": 98.10686834200123, "count": 90, "self": 39.50551661198142, "children": { "TorchPPOOptimizer.update": { "total": 58.601351730019815, "count": 4587, "self": 58.601351730019815 } } } } } } }, "trainer_threads": { "total": 8.420001904596575e-07, "count": 1, "self": 8.420001904596575e-07 }, "TrainerController._save_models": { "total": 0.09188149700003123, "count": 1, "self": 0.001107937000142556, "children": { "RLTrainer._checkpoint": { "total": 0.09077355999988868, "count": 1, "self": 0.09077355999988868 } } } } } } }