{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0544053316116333, "min": 1.0544053316116333, "max": 2.8688344955444336, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10079.060546875, "min": 10079.060546875, "max": 29379.734375, "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": 12.795098304748535, "min": 0.2699648141860962, "max": 12.795098304748535, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.044189453125, "min": 52.373172760009766, "max": 2580.62158203125, "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.Losses.PolicyLoss.mean": { "value": 0.069983686207207, "min": 0.06474577821859652, "max": 0.07392626166236405, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.279934744828828, "min": 0.25977104744878504, "max": 0.36963130831182023, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20940581665319555, "min": 0.11105704098465105, "max": 0.2767637867553561, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8376232666127822, "min": 0.4442281639386042, "max": 1.3838189337767806, "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.CumulativeReward.mean": { "value": 25.045454545454547, "min": 3.2954545454545454, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 145.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.2954545454545454, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 145.0, "max": 1405.0, "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": "1704302762", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704303204" }, "total": 442.38712112400003, "count": 1, "self": 0.44537752200017167, "children": { "run_training.setup": { "total": 0.05413975900000878, "count": 1, "self": 0.05413975900000878 }, "TrainerController.start_learning": { "total": 441.88760384299985, "count": 1, "self": 0.5373821049921617, "children": { "TrainerController._reset_env": { "total": 3.2751235979999365, "count": 1, "self": 3.2751235979999365 }, "TrainerController.advance": { "total": 437.99039639900764, "count": 18200, "self": 0.2828002240011074, "children": { "env_step": { "total": 437.70759617500653, "count": 18200, "self": 287.32509477203064, "children": { "SubprocessEnvManager._take_step": { "total": 150.1113841129884, "count": 18200, "self": 1.4252440959899104, "children": { "TorchPolicy.evaluate": { "total": 148.68614001699848, "count": 18200, "self": 148.68614001699848 } } }, "workers": { "total": 0.27111728998750095, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 440.7247517130021, "count": 18200, "is_parallel": true, "self": 217.67222335699012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006119417000036265, "count": 1, "is_parallel": true, "self": 0.004737524999768539, "children": { "_process_rank_one_or_two_observation": { "total": 0.001381892000267726, "count": 10, "is_parallel": true, "self": 0.001381892000267726 } } }, "UnityEnvironment.step": { "total": 0.0382326799999646, "count": 1, "is_parallel": true, "self": 0.0006473789999290602, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004375900000468391, "count": 1, "is_parallel": true, "self": 0.0004375900000468391 }, "communicator.exchange": { "total": 0.035285494000049766, "count": 1, "is_parallel": true, "self": 0.035285494000049766 }, "steps_from_proto": { "total": 0.001862216999938937, "count": 1, "is_parallel": true, "self": 0.00035614299986264086, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015060740000762962, "count": 10, "is_parallel": true, "self": 0.0015060740000762962 } } } } } } }, "UnityEnvironment.step": { "total": 223.05252835601198, "count": 18199, "is_parallel": true, "self": 10.639519969044272, "children": { "UnityEnvironment._generate_step_input": { "total": 5.218855593987428, "count": 18199, "is_parallel": true, "self": 5.218855593987428 }, "communicator.exchange": { "total": 174.12745710898866, "count": 18199, "is_parallel": true, "self": 174.12745710898866 }, "steps_from_proto": { "total": 33.06669568399161, "count": 18199, "is_parallel": true, "self": 6.114426241957972, "children": { "_process_rank_one_or_two_observation": { "total": 26.95226944203364, "count": 181990, "is_parallel": true, "self": 26.95226944203364 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001262499999938882, "count": 1, "self": 0.0001262499999938882, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.54193404900104, "count": 664621, "is_parallel": true, "self": 13.907771520088204, "children": { "process_trajectory": { "total": 239.17946158091308, "count": 664621, "is_parallel": true, "self": 238.39889782891305, "children": { "RLTrainer._checkpoint": { "total": 0.7805637520000346, "count": 4, "is_parallel": true, "self": 0.7805637520000346 } } }, "_update_policy": { "total": 179.45470094799975, "count": 90, "is_parallel": true, "self": 56.6362215200046, "children": { "TorchPPOOptimizer.update": { "total": 122.81847942799516, "count": 4587, "is_parallel": true, "self": 122.81847942799516 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08457549100012329, "count": 1, "self": 0.0009501980000550247, "children": { "RLTrainer._checkpoint": { "total": 0.08362529300006827, "count": 1, "self": 0.08362529300006827 } } } } } } }