{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7982149720191956, "min": 0.7982149720191956, "max": 2.8570287227630615, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7586.23486328125, "min": 7586.23486328125, "max": 29164.548828125, "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": 12.782713890075684, "min": 0.5403063893318176, "max": 12.782713890075684, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.629150390625, "min": 104.81944274902344, "max": 2588.972900390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07148878615265072, "min": 0.06487869791895969, "max": 0.07326971263140805, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2859551446106029, "min": 0.25951479167583874, "max": 0.36634856315704023, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22505806751695331, "min": 0.12027517450726866, "max": 0.31199148320684245, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9002322700678133, "min": 0.4811006980290746, "max": 1.5599574160342122, "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": 25.454545454545453, "min": 3.477272727272727, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 153.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.477272727272727, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 153.0, "max": 1391.0, "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": "1747648911", "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=SnowballTarget1.1 --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": "1747649341" }, "total": 430.381266934, "count": 1, "self": 0.42610646800017093, "children": { "run_training.setup": { "total": 0.021537986999874192, "count": 1, "self": 0.021537986999874192 }, "TrainerController.start_learning": { "total": 429.93362247899995, "count": 1, "self": 0.40889653601811915, "children": { "TrainerController._reset_env": { "total": 2.2305819969999447, "count": 1, "self": 2.2305819969999447 }, "TrainerController.advance": { "total": 427.211071688982, "count": 18192, "self": 0.4283033839806194, "children": { "env_step": { "total": 303.2150095989998, "count": 18192, "self": 232.57902675102105, "children": { "SubprocessEnvManager._take_step": { "total": 70.41335484097954, "count": 18192, "self": 1.2682653719723476, "children": { "TorchPolicy.evaluate": { "total": 69.14508946900719, "count": 18192, "self": 69.14508946900719 } } }, "workers": { "total": 0.2226280069992299, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 428.4694752400087, "count": 18192, "is_parallel": true, "self": 224.65466380800535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020275389999824256, "count": 1, "is_parallel": true, "self": 0.0006012579999605805, "children": { "_process_rank_one_or_two_observation": { "total": 0.001426281000021845, "count": 10, "is_parallel": true, "self": 0.001426281000021845 } } }, "UnityEnvironment.step": { "total": 0.03817642500007423, "count": 1, "is_parallel": true, "self": 0.0006750199997895834, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003974850001213781, "count": 1, "is_parallel": true, "self": 0.0003974850001213781 }, "communicator.exchange": { "total": 0.03490190699994855, "count": 1, "is_parallel": true, "self": 0.03490190699994855 }, "steps_from_proto": { "total": 0.00220201300021472, "count": 1, "is_parallel": true, "self": 0.0005282850004277861, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016737279997869337, "count": 10, "is_parallel": true, "self": 0.0016737279997869337 } } } } } } }, "UnityEnvironment.step": { "total": 203.81481143200335, "count": 18191, "is_parallel": true, "self": 9.657765572960216, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3392884550246436, "count": 18191, "is_parallel": true, "self": 5.3392884550246436 }, "communicator.exchange": { "total": 157.80555052401246, "count": 18191, "is_parallel": true, "self": 157.80555052401246 }, "steps_from_proto": { "total": 31.012206880006033, "count": 18191, "is_parallel": true, "self": 5.647165949998907, "children": { "_process_rank_one_or_two_observation": { "total": 25.365040930007126, "count": 181910, "is_parallel": true, "self": 25.365040930007126 } } } } } } } } } } }, "trainer_advance": { "total": 123.56775870600154, "count": 18192, "self": 0.47526991498489224, "children": { "process_trajectory": { "total": 27.119974749015455, "count": 18192, "self": 26.748411945015505, "children": { "RLTrainer._checkpoint": { "total": 0.3715628039999501, "count": 4, "self": 0.3715628039999501 } } }, "_update_policy": { "total": 95.9725140420012, "count": 90, "self": 39.01365369500468, "children": { "TorchPPOOptimizer.update": { "total": 56.95886034699652, "count": 4587, "self": 56.95886034699652 } } } } } } }, "trainer_threads": { "total": 9.629998203308787e-07, "count": 1, "self": 9.629998203308787e-07 }, "TrainerController._save_models": { "total": 0.08307129400009217, "count": 1, "self": 0.0008970550002231903, "children": { "RLTrainer._checkpoint": { "total": 0.08217423899986898, "count": 1, "self": 0.08217423899986898 } } } } } } }