{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9270309209823608, "min": 0.9270309209823608, "max": 2.8622255325317383, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8851.291015625, "min": 8851.291015625, "max": 29343.53515625, "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": 13.01202392578125, "min": 0.44474273920059204, "max": 13.01202392578125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.3447265625, "min": 86.28009033203125, "max": 2628.61962890625, "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": 0.06629582224512906, "min": 0.06401748153353658, "max": 0.0735624599321597, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26518328898051624, "min": 0.2560699261341463, "max": 0.3678067679181421, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19526282153731467, "min": 0.15636959206084627, "max": 0.29084407354102415, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7810512861492587, "min": 0.6254783682433851, "max": 1.4542203677051209, "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": 25.75, "min": 3.9318181818181817, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 173.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.9318181818181817, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 173.0, "max": 1415.0, "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": "1711262981", "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/config.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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711263430" }, "total": 448.45068225600005, "count": 1, "self": 0.44203178500004014, "children": { "run_training.setup": { "total": 0.06199018600000272, "count": 1, "self": 0.06199018600000272 }, "TrainerController.start_learning": { "total": 447.946660285, "count": 1, "self": 0.5644255549954096, "children": { "TrainerController._reset_env": { "total": 3.503316064000046, "count": 1, "self": 3.503316064000046 }, "TrainerController.advance": { "total": 443.7887487550046, "count": 18199, "self": 0.264949027998, "children": { "env_step": { "total": 443.5237997270066, "count": 18199, "self": 286.47950369401076, "children": { "SubprocessEnvManager._take_step": { "total": 156.76061592200347, "count": 18199, "self": 1.4400385200161736, "children": { "TorchPolicy.evaluate": { "total": 155.3205774019873, "count": 18199, "self": 155.3205774019873 } } }, "workers": { "total": 0.2836801109923499, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 446.84551757001134, "count": 18199, "is_parallel": true, "self": 222.73465008302003, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008144661999949676, "count": 1, "is_parallel": true, "self": 0.00407256699975278, "children": { "_process_rank_one_or_two_observation": { "total": 0.004072095000196896, "count": 10, "is_parallel": true, "self": 0.004072095000196896 } } }, "UnityEnvironment.step": { "total": 0.0346712010000374, "count": 1, "is_parallel": true, "self": 0.0006699939999634807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004017219999923327, "count": 1, "is_parallel": true, "self": 0.0004017219999923327 }, "communicator.exchange": { "total": 0.03162889999998697, "count": 1, "is_parallel": true, "self": 0.03162889999998697 }, "steps_from_proto": { "total": 0.0019705850000946157, "count": 1, "is_parallel": true, "self": 0.00036401600016233715, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016065689999322785, "count": 10, "is_parallel": true, "self": 0.0016065689999322785 } } } } } } }, "UnityEnvironment.step": { "total": 224.1108674869913, "count": 18198, "is_parallel": true, "self": 10.266648875973488, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4123501240105725, "count": 18198, "is_parallel": true, "self": 5.4123501240105725 }, "communicator.exchange": { "total": 175.02885248499865, "count": 18198, "is_parallel": true, "self": 175.02885248499865 }, "steps_from_proto": { "total": 33.4030160020086, "count": 18198, "is_parallel": true, "self": 6.343499242969756, "children": { "_process_rank_one_or_two_observation": { "total": 27.059516759038843, "count": 181980, "is_parallel": true, "self": 27.059516759038843 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011831999995592923, "count": 1, "self": 0.00011831999995592923, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 438.2315408950518, "count": 665632, "is_parallel": true, "self": 14.454092008029761, "children": { "process_trajectory": { "total": 242.08589639902152, "count": 665632, "is_parallel": true, "self": 241.49742668502154, "children": { "RLTrainer._checkpoint": { "total": 0.5884697139999844, "count": 4, "is_parallel": true, "self": 0.5884697139999844 } } }, "_update_policy": { "total": 181.69155248800053, "count": 90, "is_parallel": true, "self": 50.71567731700054, "children": { "TorchPPOOptimizer.update": { "total": 130.97587517099998, "count": 4587, "is_parallel": true, "self": 130.97587517099998 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09005159100001947, "count": 1, "self": 0.0009856829999534966, "children": { "RLTrainer._checkpoint": { "total": 0.08906590800006597, "count": 1, "self": 0.08906590800006597 } } } } } } }