{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.3138859272003174, "min": 2.3138859272003174, "max": 2.8339903354644775, "count": 5 }, "SnowballTarget.Policy.Entropy.sum": { "value": 23620.1484375, "min": 23620.1484375, "max": 28929.373046875, "count": 5 }, "SnowballTarget.Step.mean": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Step.sum": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.713239669799805, "min": 0.39039018750190735, "max": 4.713239669799805, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 914.3684692382812, "min": 75.7356948852539, "max": 914.3684692382812, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07101792926465245, "min": 0.06634338495205157, "max": 0.07218859588679419, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2840717170586098, "min": 0.2815638394498748, "max": 0.3454439147539875, "count": 5 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2875146497698391, "min": 0.0989999590491803, "max": 0.2875146497698391, "count": 5 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1500585990793564, "min": 0.3959998361967212, "max": 1.2863343296682135, "count": 5 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.9928090024000003e-05, "min": 2.9928090024000003e-05, "max": 0.00026752801082399996, "count": 5 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00011971236009600001, "min": 0.00011971236009600001, "max": 0.0010701120432959998, "count": 5 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10997600000000002, "min": 0.10997600000000002, "max": 0.18917599999999998, "count": 5 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4399040000000001, "min": 0.4399040000000001, "max": 0.8468800000000001, "count": 5 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0005078024, "min": 0.0005078024, "max": 0.0044598824, "count": 5 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0020312096, "min": 0.0020312096, "max": 0.0178395296, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 12.227272727272727, "min": 2.6818181818181817, "max": 12.227272727272727, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 538.0, "min": 118.0, "max": 581.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 12.227272727272727, "min": 2.6818181818181817, "max": 12.227272727272727, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 538.0, "min": 118.0, "max": 581.0, "count": 5 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1732676605", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732676722" }, "total": 117.60812945700002, "count": 1, "self": 0.43885327999998935, "children": { "run_training.setup": { "total": 0.056552382999939255, "count": 1, "self": 0.056552382999939255 }, "TrainerController.start_learning": { "total": 117.11272379400009, "count": 1, "self": 0.09451536700225915, "children": { "TrainerController._reset_env": { "total": 1.972023967000041, "count": 1, "self": 1.972023967000041 }, "TrainerController.advance": { "total": 114.9539014639978, "count": 4592, "self": 0.09766422199970748, "children": { "env_step": { "total": 81.06583385199156, "count": 4592, "self": 61.74178481699175, "children": { "SubprocessEnvManager._take_step": { "total": 19.26620812799797, "count": 4592, "self": 0.3593554799941785, "children": { "TorchPolicy.evaluate": { "total": 18.90685264800379, "count": 4592, "self": 18.90685264800379 } } }, "workers": { "total": 0.05784090700183242, "count": 4592, "self": 0.0, "children": { "worker_root": { "total": 116.56226213999594, "count": 4592, "is_parallel": true, "self": 62.64528356899348, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023152329999902577, "count": 1, "is_parallel": true, "self": 0.0007508009998673515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015644320001229062, "count": 10, "is_parallel": true, "self": 0.0015644320001229062 } } }, "UnityEnvironment.step": { "total": 0.04225745899998401, "count": 1, "is_parallel": true, "self": 0.0007446839999829535, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039866800000254443, "count": 1, "is_parallel": true, "self": 0.00039866800000254443 }, "communicator.exchange": { "total": 0.03890115900003366, "count": 1, "is_parallel": true, "self": 0.03890115900003366 }, "steps_from_proto": { "total": 0.002212947999964854, "count": 1, "is_parallel": true, "self": 0.0004724530001567473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017404949998081065, "count": 10, "is_parallel": true, "self": 0.0017404949998081065 } } } } } } }, "UnityEnvironment.step": { "total": 53.91697857100246, "count": 4591, "is_parallel": true, "self": 2.6096144709940745, "children": { "UnityEnvironment._generate_step_input": { "total": 1.429090691997203, "count": 4591, "is_parallel": true, "self": 1.429090691997203 }, "communicator.exchange": { "total": 41.033505354007616, "count": 4591, "is_parallel": true, "self": 41.033505354007616 }, "steps_from_proto": { "total": 8.844768054003566, "count": 4591, "is_parallel": true, "self": 1.6128092089958272, "children": { "_process_rank_one_or_two_observation": { "total": 7.231958845007739, "count": 45910, "is_parallel": true, "self": 7.231958845007739 } } } } } } } } } } }, "trainer_advance": { "total": 33.79040339000653, "count": 4592, "self": 0.11972088699519645, "children": { "process_trajectory": { "total": 8.159988817011254, "count": 4592, "self": 7.559814683011155, "children": { "RLTrainer._checkpoint": { "total": 0.600174134000099, "count": 5, "self": 0.600174134000099 } } }, "_update_policy": { "total": 25.51069368600008, "count": 22, "self": 10.273556020000683, "children": { "TorchPPOOptimizer.update": { "total": 15.237137665999398, "count": 1119, "self": 15.237137665999398 } } } } } } }, "trainer_threads": { "total": 9.780001164472196e-07, "count": 1, "self": 9.780001164472196e-07 }, "TrainerController._save_models": { "total": 0.09228201799987801, "count": 1, "self": 0.0008890579997569148, "children": { "RLTrainer._checkpoint": { "total": 0.09139296000012109, "count": 1, "self": 0.09139296000012109 } } } } } } }