{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9536555409431458, "min": 0.9536555409431458, "max": 2.8648746013641357, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9126.4833984375, "min": 9126.4833984375, "max": 29307.66796875, "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": 12.120377540588379, "min": 0.5005871653556824, "max": 12.120377540588379, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2363.4736328125, "min": 97.11390686035156, "max": 2462.99755859375, "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": 0.07416584400526322, "min": 0.060521857589757186, "max": 0.07416584400526322, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29666337602105286, "min": 0.2545102020572349, "max": 0.36240136511111687, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19188438304791264, "min": 0.139070637863102, "max": 0.27056364276829886, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7675375321916506, "min": 0.556282551452408, "max": 1.3528182138414944, "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": 24.0, "min": 3.6136363636363638, "max": 24.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1056.0, "min": 159.0, "max": 1313.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.0, "min": 3.6136363636363638, "max": 24.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1056.0, "min": 159.0, "max": 1313.0, "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": "1687371985", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ../SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687372442" }, "total": 456.51218383599996, "count": 1, "self": 0.4347511419998682, "children": { "run_training.setup": { "total": 0.040726142000039545, "count": 1, "self": 0.040726142000039545 }, "TrainerController.start_learning": { "total": 456.03670655200006, "count": 1, "self": 0.5182648669963328, "children": { "TrainerController._reset_env": { "total": 4.06444292499998, "count": 1, "self": 4.06444292499998 }, "TrainerController.advance": { "total": 451.31795872000384, "count": 18204, "self": 0.25138146301173947, "children": { "env_step": { "total": 451.0665772569921, "count": 18204, "self": 332.47472396499427, "children": { "SubprocessEnvManager._take_step": { "total": 118.34339952800838, "count": 18204, "self": 1.7804989350094047, "children": { "TorchPolicy.evaluate": { "total": 116.56290059299897, "count": 18204, "self": 116.56290059299897 } } }, "workers": { "total": 0.24845376398945973, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 454.49946128399074, "count": 18204, "is_parallel": true, "self": 215.0664651369932, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00527052100005676, "count": 1, "is_parallel": true, "self": 0.0038325230001419186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014379979999148418, "count": 10, "is_parallel": true, "self": 0.0014379979999148418 } } }, "UnityEnvironment.step": { "total": 0.03383959099994627, "count": 1, "is_parallel": true, "self": 0.0006149819998881867, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003102090000766111, "count": 1, "is_parallel": true, "self": 0.0003102090000766111 }, "communicator.exchange": { "total": 0.030892068999946787, "count": 1, "is_parallel": true, "self": 0.030892068999946787 }, "steps_from_proto": { "total": 0.002022331000034683, "count": 1, "is_parallel": true, "self": 0.0003789799998230592, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016433510002116236, "count": 10, "is_parallel": true, "self": 0.0016433510002116236 } } } } } } }, "UnityEnvironment.step": { "total": 239.43299614699754, "count": 18203, "is_parallel": true, "self": 10.03784451601075, "children": { "UnityEnvironment._generate_step_input": { "total": 4.976317172994186, "count": 18203, "is_parallel": true, "self": 4.976317172994186 }, "communicator.exchange": { "total": 191.21412274899797, "count": 18203, "is_parallel": true, "self": 191.21412274899797 }, "steps_from_proto": { "total": 33.20471170899464, "count": 18203, "is_parallel": true, "self": 5.967694236976968, "children": { "_process_rank_one_or_two_observation": { "total": 27.23701747201767, "count": 182030, "is_parallel": true, "self": 27.23701747201767 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015011400000730646, "count": 1, "self": 0.00015011400000730646, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.7775096260358, "count": 439846, "is_parallel": true, "self": 10.00371058107396, "children": { "process_trajectory": { "total": 245.29526926896222, "count": 439846, "is_parallel": true, "self": 243.60576360196205, "children": { "RLTrainer._checkpoint": { "total": 1.6895056670001622, "count": 4, "is_parallel": true, "self": 1.6895056670001622 } } }, "_update_policy": { "total": 192.47852977599962, "count": 90, "is_parallel": true, "self": 79.76756330099715, "children": { "TorchPPOOptimizer.update": { "total": 112.71096647500246, "count": 4587, "is_parallel": true, "self": 112.71096647500246 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1358899259998907, "count": 1, "self": 0.0008473849998154037, "children": { "RLTrainer._checkpoint": { "total": 0.1350425410000753, "count": 1, "self": 0.1350425410000753 } } } } } } }