{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8727388381958008, "min": 0.8727388381958008, "max": 2.859950304031372, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8294.509765625, "min": 8294.509765625, "max": 29194.373046875, "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": 12.073390007019043, "min": 0.3272010087966919, "max": 12.073390007019043, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2354.31103515625, "min": 63.47699737548828, "max": 2432.07470703125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06784338405408312, "min": 0.06266626868958103, "max": 0.07769250010103718, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2713735362163325, "min": 0.2506650747583241, "max": 0.36820615537626683, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1740870437055242, "min": 0.14124484087669237, "max": 0.30254819711633757, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6963481748220968, "min": 0.5649793635067695, "max": 1.4485027719946468, "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": 24.045454545454547, "min": 3.3636363636363638, "max": 24.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1058.0, "min": 148.0, "max": 1304.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.045454545454547, "min": 3.3636363636363638, "max": 24.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1058.0, "min": 148.0, "max": 1304.0, "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": "1753751057", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn --force ./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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753751503" }, "total": 445.55032676199994, "count": 1, "self": 0.4250521659998867, "children": { "run_training.setup": { "total": 0.020524522999949113, "count": 1, "self": 0.020524522999949113 }, "TrainerController.start_learning": { "total": 445.1047500730001, "count": 1, "self": 0.4144425640056397, "children": { "TrainerController._reset_env": { "total": 2.802590791000057, "count": 1, "self": 2.802590791000057 }, "TrainerController.advance": { "total": 441.80432086599467, "count": 18192, "self": 0.4438711269910982, "children": { "env_step": { "total": 320.0461651900048, "count": 18192, "self": 245.65108587999566, "children": { "SubprocessEnvManager._take_step": { "total": 74.15378722800301, "count": 18192, "self": 1.3069287319899558, "children": { "TorchPolicy.evaluate": { "total": 72.84685849601306, "count": 18192, "self": 72.84685849601306 } } }, "workers": { "total": 0.24129208200611174, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 443.469420803975, "count": 18192, "is_parallel": true, "self": 228.67773073498915, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027554450000479846, "count": 1, "is_parallel": true, "self": 0.0007856790000460023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019697660000019823, "count": 10, "is_parallel": true, "self": 0.0019697660000019823 } } }, "UnityEnvironment.step": { "total": 0.038197294000156035, "count": 1, "is_parallel": true, "self": 0.0005860120002125768, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003908029998456186, "count": 1, "is_parallel": true, "self": 0.0003908029998456186 }, "communicator.exchange": { "total": 0.035220563999928345, "count": 1, "is_parallel": true, "self": 0.035220563999928345 }, "steps_from_proto": { "total": 0.0019999150001694943, "count": 1, "is_parallel": true, "self": 0.00038565600061701844, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016142589995524759, "count": 10, "is_parallel": true, "self": 0.0016142589995524759 } } } } } } }, "UnityEnvironment.step": { "total": 214.79169006898587, "count": 18191, "is_parallel": true, "self": 9.967267691977668, "children": { "UnityEnvironment._generate_step_input": { "total": 5.565313077019255, "count": 18191, "is_parallel": true, "self": 5.565313077019255 }, "communicator.exchange": { "total": 166.2590352159832, "count": 18191, "is_parallel": true, "self": 166.2590352159832 }, "steps_from_proto": { "total": 33.000074084005746, "count": 18191, "is_parallel": true, "self": 6.106835263030234, "children": { "_process_rank_one_or_two_observation": { "total": 26.89323882097551, "count": 181910, "is_parallel": true, "self": 26.89323882097551 } } } } } } } } } } }, "trainer_advance": { "total": 121.31428454899878, "count": 18192, "self": 0.5168278019948502, "children": { "process_trajectory": { "total": 27.387880353003993, "count": 18192, "self": 26.972582727004237, "children": { "RLTrainer._checkpoint": { "total": 0.41529762599975584, "count": 4, "self": 0.41529762599975584 } } }, "_update_policy": { "total": 93.40957639399994, "count": 90, "self": 38.1733674989955, "children": { "TorchPPOOptimizer.update": { "total": 55.23620889500444, "count": 4587, "self": 55.23620889500444 } } } } } } }, "trainer_threads": { "total": 9.51999936660286e-07, "count": 1, "self": 9.51999936660286e-07 }, "TrainerController._save_models": { "total": 0.08339489999980287, "count": 1, "self": 0.0010308849996363278, "children": { "RLTrainer._checkpoint": { "total": 0.08236401500016655, "count": 1, "self": 0.08236401500016655 } } } } } } }