{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9017645120620728, "min": 0.9017645120620728, "max": 2.853071689605713, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8570.3701171875, "min": 8570.3701171875, "max": 29124.15625, "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": 12.805849075317383, "min": 0.29814305901527405, "max": 12.805849075317383, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2497.140625, "min": 57.83975601196289, "max": 2593.414306640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06875203884769956, "min": 0.06047927139892286, "max": 0.07650595430773226, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27500815539079826, "min": 0.24191708559569144, "max": 0.3618520309112272, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19421784375228135, "min": 0.11974284284994663, "max": 0.27482886004681684, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7768713750091254, "min": 0.4789713713997865, "max": 1.374144300234084, "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": 25.272727272727273, "min": 3.6818181818181817, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 162.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.6818181818181817, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 162.0, "max": 1390.0, "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": "1767513876", "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": "1767514300" }, "total": 424.35044245799963, "count": 1, "self": 0.4345214289996875, "children": { "run_training.setup": { "total": 0.028989925000132644, "count": 1, "self": 0.028989925000132644 }, "TrainerController.start_learning": { "total": 423.8869311039998, "count": 1, "self": 0.331131575906511, "children": { "TrainerController._reset_env": { "total": 3.0439852049994442, "count": 1, "self": 3.0439852049994442 }, "TrainerController.advance": { "total": 420.4375400510935, "count": 18192, "self": 0.34719964614396304, "children": { "env_step": { "total": 304.8247216479367, "count": 18192, "self": 238.7081301809676, "children": { "SubprocessEnvManager._take_step": { "total": 65.91630649495983, "count": 18192, "self": 1.1961646278723492, "children": { "TorchPolicy.evaluate": { "total": 64.72014186708748, "count": 18192, "self": 64.72014186708748 } } }, "workers": { "total": 0.2002849720092854, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 422.1773752290219, "count": 18192, "is_parallel": true, "self": 212.20535010297135, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005435789999864937, "count": 1, "is_parallel": true, "self": 0.003788497998357343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016472920015075943, "count": 10, "is_parallel": true, "self": 0.0016472920015075943 } } }, "UnityEnvironment.step": { "total": 0.03577013399990392, "count": 1, "is_parallel": true, "self": 0.0005934099990554387, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000413251000281889, "count": 1, "is_parallel": true, "self": 0.000413251000281889 }, "communicator.exchange": { "total": 0.03279349500007811, "count": 1, "is_parallel": true, "self": 0.03279349500007811 }, "steps_from_proto": { "total": 0.0019699780004884815, "count": 1, "is_parallel": true, "self": 0.0004136380011914298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015563399992970517, "count": 10, "is_parallel": true, "self": 0.0015563399992970517 } } } } } } }, "UnityEnvironment.step": { "total": 209.97202512605054, "count": 18191, "is_parallel": true, "self": 10.074797568251597, "children": { "UnityEnvironment._generate_step_input": { "total": 5.321868723886837, "count": 18191, "is_parallel": true, "self": 5.321868723886837 }, "communicator.exchange": { "total": 159.87767173594148, "count": 18191, "is_parallel": true, "self": 159.87767173594148 }, "steps_from_proto": { "total": 34.69768709797063, "count": 18191, "is_parallel": true, "self": 6.202608277123545, "children": { "_process_rank_one_or_two_observation": { "total": 28.495078820847084, "count": 181910, "is_parallel": true, "self": 28.495078820847084 } } } } } } } } } } }, "trainer_advance": { "total": 115.26561875701282, "count": 18192, "self": 0.4231457249788946, "children": { "process_trajectory": { "total": 25.028677172033895, "count": 18192, "self": 24.54796094703397, "children": { "RLTrainer._checkpoint": { "total": 0.4807162249999237, "count": 4, "self": 0.4807162249999237 } } }, "_update_policy": { "total": 89.81379586000003, "count": 90, "self": 36.554692377982974, "children": { "TorchPPOOptimizer.update": { "total": 53.25910348201705, "count": 4587, "self": 53.25910348201705 } } } } } } }, "trainer_threads": { "total": 8.670003808219917e-07, "count": 1, "self": 8.670003808219917e-07 }, "TrainerController._save_models": { "total": 0.07427340499998536, "count": 1, "self": 0.0008836839997456991, "children": { "RLTrainer._checkpoint": { "total": 0.07338972100023966, "count": 1, "self": 0.07338972100023966 } } } } } } }