{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7816058397293091, "min": 0.7726664543151855, "max": 2.858652114868164, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7428.3818359375, "min": 7428.3818359375, "max": 29181.12109375, "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": 12.940938949584961, "min": 0.2760256826877594, "max": 12.940938949584961, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.483154296875, "min": 53.548980712890625, "max": 2607.0078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07130112766183219, "min": 0.06382371477928817, "max": 0.07319046029846835, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28520451064732877, "min": 0.26117461125421176, "max": 0.365310483288554, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21583240588798241, "min": 0.11991804243777604, "max": 0.2972485492042467, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8633296235519297, "min": 0.47967216975110416, "max": 1.4862427460212335, "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": 25.181818181818183, "min": 3.340909090909091, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 147.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 3.340909090909091, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 147.0, "max": 1397.0, "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": "1734106996", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --force --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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734107410" }, "total": 413.53150454400003, "count": 1, "self": 0.6789466750000202, "children": { "run_training.setup": { "total": 0.055266990999996324, "count": 1, "self": 0.055266990999996324 }, "TrainerController.start_learning": { "total": 412.797290878, "count": 1, "self": 0.31403428499993424, "children": { "TrainerController._reset_env": { "total": 2.0232757509999715, "count": 1, "self": 2.0232757509999715 }, "TrainerController.advance": { "total": 410.3354611480001, "count": 18192, "self": 0.3304052959947512, "children": { "env_step": { "total": 283.8362070639987, "count": 18192, "self": 216.58188820500175, "children": { "SubprocessEnvManager._take_step": { "total": 67.057957522006, "count": 18192, "self": 1.1656794970082842, "children": { "TorchPolicy.evaluate": { "total": 65.89227802499772, "count": 18192, "self": 65.89227802499772 } } }, "workers": { "total": 0.1963613369909467, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 411.3697138049962, "count": 18192, "is_parallel": true, "self": 221.57579790398626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002567518999967433, "count": 1, "is_parallel": true, "self": 0.0008454590000610551, "children": { "_process_rank_one_or_two_observation": { "total": 0.001722059999906378, "count": 10, "is_parallel": true, "self": 0.001722059999906378 } } }, "UnityEnvironment.step": { "total": 0.03408668800000214, "count": 1, "is_parallel": true, "self": 0.0006541140000422274, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003748390000168911, "count": 1, "is_parallel": true, "self": 0.0003748390000168911 }, "communicator.exchange": { "total": 0.031202812999993057, "count": 1, "is_parallel": true, "self": 0.031202812999993057 }, "steps_from_proto": { "total": 0.0018549219999499655, "count": 1, "is_parallel": true, "self": 0.0003696579999541427, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014852639999958228, "count": 10, "is_parallel": true, "self": 0.0014852639999958228 } } } } } } }, "UnityEnvironment.step": { "total": 189.79391590100994, "count": 18191, "is_parallel": true, "self": 9.64254614100696, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3968553500041025, "count": 18191, "is_parallel": true, "self": 5.3968553500041025 }, "communicator.exchange": { "total": 144.00439275599712, "count": 18191, "is_parallel": true, "self": 144.00439275599712 }, "steps_from_proto": { "total": 30.75012165400176, "count": 18191, "is_parallel": true, "self": 5.377075665995619, "children": { "_process_rank_one_or_two_observation": { "total": 25.37304598800614, "count": 181910, "is_parallel": true, "self": 25.37304598800614 } } } } } } } } } } }, "trainer_advance": { "total": 126.16884878800664, "count": 18192, "self": 0.38615756300907833, "children": { "process_trajectory": { "total": 27.157448068997212, "count": 18192, "self": 26.614880157997334, "children": { "RLTrainer._checkpoint": { "total": 0.5425679109998782, "count": 4, "self": 0.5425679109998782 } } }, "_update_policy": { "total": 98.62524315600035, "count": 90, "self": 40.70690068000226, "children": { "TorchPPOOptimizer.update": { "total": 57.91834247599809, "count": 4587, "self": 57.91834247599809 } } } } } } }, "trainer_threads": { "total": 1.570999984323862e-06, "count": 1, "self": 1.570999984323862e-06 }, "TrainerController._save_models": { "total": 0.12451812300002985, "count": 1, "self": 0.002839812000047459, "children": { "RLTrainer._checkpoint": { "total": 0.12167831099998239, "count": 1, "self": 0.12167831099998239 } } } } } } }