{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7959206104278564, "min": 0.7959206104278564, "max": 2.870500326156616, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7564.4296875, "min": 7564.4296875, "max": 29302.06640625, "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": 13.265119552612305, "min": 0.3125430643558502, "max": 13.282258033752441, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2586.6982421875, "min": 60.63335418701172, "max": 2709.58056640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07174888229072916, "min": 0.06420395567832862, "max": 0.07285742302469861, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28699552916291665, "min": 0.2628554745826085, "max": 0.3630584697301874, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22179820125593858, "min": 0.0859725954291849, "max": 0.3176504635051185, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8871928050237543, "min": 0.3438903817167396, "max": 1.4884203111424164, "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": 25.34090909090909, "min": 2.6136363636363638, "max": 26.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 115.0, "max": 1431.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 2.6136363636363638, "max": 26.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 115.0, "max": 1431.0, "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": "1746403869", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746404320" }, "total": 451.43560561799995, "count": 1, "self": 0.43611078100013856, "children": { "run_training.setup": { "total": 0.024080703999970865, "count": 1, "self": 0.024080703999970865 }, "TrainerController.start_learning": { "total": 450.97541413299984, "count": 1, "self": 0.3912472880031146, "children": { "TrainerController._reset_env": { "total": 3.0488340429999425, "count": 1, "self": 3.0488340429999425 }, "TrainerController.advance": { "total": 447.43401687099697, "count": 18192, "self": 0.41975168598617074, "children": { "env_step": { "total": 320.3230336480061, "count": 18192, "self": 242.92727900000887, "children": { "SubprocessEnvManager._take_step": { "total": 77.16897595900446, "count": 18192, "self": 1.3760908060066868, "children": { "TorchPolicy.evaluate": { "total": 75.79288515299777, "count": 18192, "self": 75.79288515299777 } } }, "workers": { "total": 0.22677868899279474, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 449.46476900701157, "count": 18192, "is_parallel": true, "self": 236.80901412603657, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005581767999956355, "count": 1, "is_parallel": true, "self": 0.003430127999990873, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021516399999654823, "count": 10, "is_parallel": true, "self": 0.0021516399999654823 } } }, "UnityEnvironment.step": { "total": 0.03718373200001679, "count": 1, "is_parallel": true, "self": 0.0005696000001762513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003757629999654455, "count": 1, "is_parallel": true, "self": 0.0003757629999654455 }, "communicator.exchange": { "total": 0.034303889999932835, "count": 1, "is_parallel": true, "self": 0.034303889999932835 }, "steps_from_proto": { "total": 0.0019344789999422574, "count": 1, "is_parallel": true, "self": 0.0003910939999514085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015433849999908489, "count": 10, "is_parallel": true, "self": 0.0015433849999908489 } } } } } } }, "UnityEnvironment.step": { "total": 212.655754880975, "count": 18191, "is_parallel": true, "self": 10.000847836999583, "children": { "UnityEnvironment._generate_step_input": { "total": 5.714440160990762, "count": 18191, "is_parallel": true, "self": 5.714440160990762 }, "communicator.exchange": { "total": 163.45851662299094, "count": 18191, "is_parallel": true, "self": 163.45851662299094 }, "steps_from_proto": { "total": 33.48195025999371, "count": 18191, "is_parallel": true, "self": 6.108693176007364, "children": { "_process_rank_one_or_two_observation": { "total": 27.373257083986346, "count": 181910, "is_parallel": true, "self": 27.373257083986346 } } } } } } } } } } }, "trainer_advance": { "total": 126.69123153700468, "count": 18192, "self": 0.4905687750156176, "children": { "process_trajectory": { "total": 28.997568637990298, "count": 18192, "self": 28.577862062990675, "children": { "RLTrainer._checkpoint": { "total": 0.4197065749996227, "count": 4, "self": 0.4197065749996227 } } }, "_update_policy": { "total": 97.20309412399877, "count": 90, "self": 39.369059409996225, "children": { "TorchPPOOptimizer.update": { "total": 57.83403471400254, "count": 4587, "self": 57.83403471400254 } } } } } } }, "trainer_threads": { "total": 1.1449999419710366e-06, "count": 1, "self": 1.1449999419710366e-06 }, "TrainerController._save_models": { "total": 0.10131478599987531, "count": 1, "self": 0.000897232999705011, "children": { "RLTrainer._checkpoint": { "total": 0.1004175530001703, "count": 1, "self": 0.1004175530001703 } } } } } } }