{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1651169061660767, "min": 1.1651169061660767, "max": 2.8150293827056885, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11073.271484375, "min": 11073.271484375, "max": 28735.8203125, "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": 10.58354663848877, "min": 0.2709352672100067, "max": 10.58354663848877, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2063.79150390625, "min": 52.56144332885742, "max": 2084.54833984375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06839698165501484, "min": 0.06811188997791545, "max": 0.07602943623070828, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2735879266200594, "min": 0.2730634265706091, "max": 0.3801471811535414, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23471775935853229, "min": 0.1037013243390795, "max": 0.24586432884611625, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9388710374341291, "min": 0.414805297356318, "max": 1.2085421043174231, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600005e-05, "min": 8.082009730600005e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003232803892240002, "min": 0.0003232803892240002, "max": 0.013851600038280003, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "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": 21.568181818181817, "min": 3.1136363636363638, "max": 21.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 949.0, "min": 137.0, "max": 1151.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.568181818181817, "min": 3.1136363636363638, "max": 21.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 949.0, "min": 137.0, "max": 1151.0, "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": "1742467354", "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 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742467932" }, "total": 577.7706790910001, "count": 1, "self": 0.43410003400026653, "children": { "run_training.setup": { "total": 0.029343415999960598, "count": 1, "self": 0.029343415999960598 }, "TrainerController.start_learning": { "total": 577.3072356409999, "count": 1, "self": 0.33415302800699465, "children": { "TrainerController._reset_env": { "total": 3.559874146000084, "count": 1, "self": 3.559874146000084 }, "TrainerController.advance": { "total": 573.3258320139929, "count": 18192, "self": 0.363033319989313, "children": { "env_step": { "total": 306.8725736529942, "count": 18192, "self": 234.50002417299766, "children": { "SubprocessEnvManager._take_step": { "total": 72.17142678200355, "count": 18192, "self": 1.2850452920112048, "children": { "TorchPolicy.evaluate": { "total": 70.88638148999235, "count": 18192, "self": 70.88638148999235 } } }, "workers": { "total": 0.2011226979930143, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 575.9216862720002, "count": 18192, "is_parallel": true, "self": 369.7280999459889, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006665286000043125, "count": 1, "is_parallel": true, "self": 0.003953378000460361, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027119079995827633, "count": 10, "is_parallel": true, "self": 0.0027119079995827633 } } }, "UnityEnvironment.step": { "total": 0.03588704300000245, "count": 1, "is_parallel": true, "self": 0.0005899999998746353, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003844510000590162, "count": 1, "is_parallel": true, "self": 0.0003844510000590162 }, "communicator.exchange": { "total": 0.03301161100000627, "count": 1, "is_parallel": true, "self": 0.03301161100000627 }, "steps_from_proto": { "total": 0.0019009810000625293, "count": 1, "is_parallel": true, "self": 0.0003987410001400349, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015022399999224945, "count": 10, "is_parallel": true, "self": 0.0015022399999224945 } } } } } } }, "UnityEnvironment.step": { "total": 206.1935863260113, "count": 18191, "is_parallel": true, "self": 9.79840488302932, "children": { "UnityEnvironment._generate_step_input": { "total": 5.318757484988623, "count": 18191, "is_parallel": true, "self": 5.318757484988623 }, "communicator.exchange": { "total": 159.63388499199095, "count": 18191, "is_parallel": true, "self": 159.63388499199095 }, "steps_from_proto": { "total": 31.442538966002417, "count": 18191, "is_parallel": true, "self": 5.649342162973312, "children": { "_process_rank_one_or_two_observation": { "total": 25.793196803029105, "count": 181910, "is_parallel": true, "self": 25.793196803029105 } } } } } } } } } } }, "trainer_advance": { "total": 266.0902250410094, "count": 18192, "self": 0.42623994702557866, "children": { "process_trajectory": { "total": 28.10805753598447, "count": 18192, "self": 27.644911556984425, "children": { "RLTrainer._checkpoint": { "total": 0.4631459790000463, "count": 4, "self": 0.4631459790000463 } } }, "_update_policy": { "total": 237.55592755799933, "count": 90, "self": 93.17522783200445, "children": { "TorchPPOOptimizer.update": { "total": 144.38069972599487, "count": 12232, "self": 144.38069972599487 } } } } } } }, "trainer_threads": { "total": 1.461000010749558e-06, "count": 1, "self": 1.461000010749558e-06 }, "TrainerController._save_models": { "total": 0.08737499199992271, "count": 1, "self": 0.0008967359999587643, "children": { "RLTrainer._checkpoint": { "total": 0.08647825599996395, "count": 1, "self": 0.08647825599996395 } } } } } } }