{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7672277092933655, "min": 0.7672277092933655, "max": 2.841219902038574, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7291.73193359375, "min": 7291.73193359375, "max": 29003.171875, "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": 13.02636432647705, "min": 0.4182239770889282, "max": 13.083320617675781, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.14111328125, "min": 81.13545227050781, "max": 2668.997314453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.062054678258659, "min": 0.062054678258659, "max": 0.07734817162189775, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.248218713034636, "min": 0.248218713034636, "max": 0.3567346007273277, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19506497849144186, "min": 0.12308375357750657, "max": 0.2943920040977936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7802599139657674, "min": 0.4923350143100263, "max": 1.4716718690652475, "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": 25.113636363636363, "min": 3.4318181818181817, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 151.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.4318181818181817, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 151.0, "max": 1418.0, "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": "1768337102", "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": "1768337540" }, "total": 437.9767446379999, "count": 1, "self": 0.43128314599994155, "children": { "run_training.setup": { "total": 0.024939097000014954, "count": 1, "self": 0.024939097000014954 }, "TrainerController.start_learning": { "total": 437.52052239499994, "count": 1, "self": 0.3845260700095423, "children": { "TrainerController._reset_env": { "total": 3.067694898000127, "count": 1, "self": 3.067694898000127 }, "TrainerController.advance": { "total": 433.97682877699026, "count": 18192, "self": 0.39748562901831974, "children": { "env_step": { "total": 316.64553098999704, "count": 18192, "self": 247.6373981780116, "children": { "SubprocessEnvManager._take_step": { "total": 68.77594609898256, "count": 18192, "self": 1.2627790109715988, "children": { "TorchPolicy.evaluate": { "total": 67.51316708801096, "count": 18192, "self": 67.51316708801096 } } }, "workers": { "total": 0.23218671300287497, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 435.66740860700565, "count": 18192, "is_parallel": true, "self": 218.2867620009988, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004585541000096782, "count": 1, "is_parallel": true, "self": 0.003223493000405142, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013620479996916401, "count": 10, "is_parallel": true, "self": 0.0013620479996916401 } } }, "UnityEnvironment.step": { "total": 0.06515467999997782, "count": 1, "is_parallel": true, "self": 0.0005621269999664946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003723239999544603, "count": 1, "is_parallel": true, "self": 0.0003723239999544603 }, "communicator.exchange": { "total": 0.06238142999995944, "count": 1, "is_parallel": true, "self": 0.06238142999995944 }, "steps_from_proto": { "total": 0.0018387990000974241, "count": 1, "is_parallel": true, "self": 0.0003517049999572919, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014870940001401323, "count": 10, "is_parallel": true, "self": 0.0014870940001401323 } } } } } } }, "UnityEnvironment.step": { "total": 217.38064660600685, "count": 18191, "is_parallel": true, "self": 10.071094475970085, "children": { "UnityEnvironment._generate_step_input": { "total": 5.431637311021859, "count": 18191, "is_parallel": true, "self": 5.431637311021859 }, "communicator.exchange": { "total": 166.26849075401083, "count": 18191, "is_parallel": true, "self": 166.26849075401083 }, "steps_from_proto": { "total": 35.60942406500408, "count": 18191, "is_parallel": true, "self": 6.622163983011205, "children": { "_process_rank_one_or_two_observation": { "total": 28.987260081992872, "count": 181910, "is_parallel": true, "self": 28.987260081992872 } } } } } } } } } } }, "trainer_advance": { "total": 116.9338121579749, "count": 18192, "self": 0.49436150496831033, "children": { "process_trajectory": { "total": 25.447807963007108, "count": 18192, "self": 25.07714812800714, "children": { "RLTrainer._checkpoint": { "total": 0.37065983499996946, "count": 4, "self": 0.37065983499996946 } } }, "_update_policy": { "total": 90.99164268999948, "count": 90, "self": 37.49035498099943, "children": { "TorchPPOOptimizer.update": { "total": 53.50128770900005, "count": 4587, "self": 53.50128770900005 } } } } } } }, "trainer_threads": { "total": 9.560001217323588e-07, "count": 1, "self": 9.560001217323588e-07 }, "TrainerController._save_models": { "total": 0.09147169399989252, "count": 1, "self": 0.0007068949998938479, "children": { "RLTrainer._checkpoint": { "total": 0.09076479899999867, "count": 1, "self": 0.09076479899999867 } } } } } } }