{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7442439794540405, "min": 0.7442439794540405, "max": 2.7657876014709473, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7073.294921875, "min": 7073.294921875, "max": 28233.16015625, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.381776809692383, "min": 0.1888207048177719, "max": 9.381776809692383, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1820.064697265625, "min": 36.63121795654297, "max": 1835.51904296875, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07153538260724203, "min": 0.06945479740348173, "max": 0.08686302093647742, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2861415304289681, "min": 0.28352255177653884, "max": 0.4343151046823871, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.223554309077707, "min": 0.10499871192253468, "max": 0.33912150621414183, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.894217236310828, "min": 0.41999484769013873, "max": 1.6956075310707093, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.576009808480004e-05, "min": 9.576009808480004e-05, "max": 0.0048917600021648, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00038304039233920016, "min": 0.00038304039233920016, "max": 0.023468800030623998, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000003, "min": 0.10191520000000003, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4076608000000001, "min": 0.4076608000000001, "max": 0.9693759999999998, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000004, "min": 0.00010556848000000004, "max": 0.00489197648, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00042227392000000015, "min": 0.00042227392000000015, "max": 0.023471862399999998, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.136363636363637, "min": 2.8863636363636362, "max": 19.136363636363637, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 842.0, "min": 127.0, "max": 1028.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.136363636363637, "min": 2.8863636363636362, "max": 19.136363636363637, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 842.0, "min": 127.0, "max": 1028.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733348432", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1733349427" }, "total": 995.18091472, "count": 1, "self": 0.42473721200019554, "children": { "run_training.setup": { "total": 0.05524678799997673, "count": 1, "self": 0.05524678799997673 }, "TrainerController.start_learning": { "total": 994.7009307199999, "count": 1, "self": 0.4023459320051188, "children": { "TrainerController._reset_env": { "total": 2.0214815539999904, "count": 1, "self": 2.0214815539999904 }, "TrainerController.advance": { "total": 992.1816376149948, "count": 22728, "self": 0.4321230559989999, "children": { "env_step": { "total": 358.85163075801034, "count": 22728, "self": 272.638975668994, "children": { "SubprocessEnvManager._take_step": { "total": 85.9567832580035, "count": 22728, "self": 1.4954264490114042, "children": { "TorchPolicy.evaluate": { "total": 84.4613568089921, "count": 22728, "self": 84.4613568089921 } } }, "workers": { "total": 0.2558718310128256, "count": 22728, "self": 0.0, "children": { "worker_root": { "total": 993.1754252380239, "count": 22728, "is_parallel": true, "self": 754.0896102000095, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022979139999961262, "count": 1, "is_parallel": true, "self": 0.0006599379999556731, "children": { "_process_rank_one_or_two_observation": { "total": 0.001637976000040453, "count": 10, "is_parallel": true, "self": 0.001637976000040453 } } }, "UnityEnvironment.step": { "total": 0.034921768000003794, "count": 1, "is_parallel": true, "self": 0.0006384850000245024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004067509999572394, "count": 1, "is_parallel": true, "self": 0.0004067509999572394 }, "communicator.exchange": { "total": 0.03196540400000458, "count": 1, "is_parallel": true, "self": 0.03196540400000458 }, "steps_from_proto": { "total": 0.0019111280000174702, "count": 1, "is_parallel": true, "self": 0.00036357900000894006, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015475490000085301, "count": 10, "is_parallel": true, "self": 0.0015475490000085301 } } } } } } }, "UnityEnvironment.step": { "total": 239.0858150380144, "count": 22727, "is_parallel": true, "self": 12.18620896700952, "children": { "UnityEnvironment._generate_step_input": { "total": 6.712104179983555, "count": 22727, "is_parallel": true, "self": 6.712104179983555 }, "communicator.exchange": { "total": 181.40161359101847, "count": 22727, "is_parallel": true, "self": 181.40161359101847 }, "steps_from_proto": { "total": 38.78588830000285, "count": 22727, "is_parallel": true, "self": 6.781919754000398, "children": { "_process_rank_one_or_two_observation": { "total": 32.003968546002454, "count": 227270, "is_parallel": true, "self": 32.003968546002454 } } } } } } } } } } }, "trainer_advance": { "total": 632.8978838009854, "count": 22728, "self": 0.5026090619876413, "children": { "process_trajectory": { "total": 32.77365163199818, "count": 22728, "self": 32.21942843899831, "children": { "RLTrainer._checkpoint": { "total": 0.5542231929998707, "count": 5, "self": 0.5542231929998707 } } }, "_update_policy": { "total": 599.6216231069996, "count": 113, "self": 247.33070611501148, "children": { "TorchPPOOptimizer.update": { "total": 352.29091699198807, "count": 28800, "self": 352.29091699198807 } } } } } } }, "trainer_threads": { "total": 1.0779999684018549e-06, "count": 1, "self": 1.0779999684018549e-06 }, "TrainerController._save_models": { "total": 0.09546454099995572, "count": 1, "self": 0.000878545999967173, "children": { "RLTrainer._checkpoint": { "total": 0.09458599499998854, "count": 1, "self": 0.09458599499998854 } } } } } } }