{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9969991445541382, "min": 0.9969991445541382, "max": 2.8748538494110107, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9519.34765625, "min": 9519.34765625, "max": 29441.37890625, "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": 12.912104606628418, "min": 0.13666932284832, "max": 12.945841789245605, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2517.8603515625, "min": 26.51384735107422, "max": 2640.95166015625, "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": 0.06933611396280136, "min": 0.06093968456472937, "max": 0.07518565922448534, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27734445585120543, "min": 0.24375873825891747, "max": 0.3759282961224267, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18889656914945913, "min": 0.08128619360664457, "max": 0.29364556709633155, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7555862765978365, "min": 0.3251447744265783, "max": 1.3066910835457783, "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": 25.113636363636363, "min": 2.227272727272727, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 98.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 2.227272727272727, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 98.0, "max": 1402.0, "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": "1675374065", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675374509" }, "total": 443.883233585, "count": 1, "self": 0.43942818400006445, "children": { "run_training.setup": { "total": 0.10300147099997048, "count": 1, "self": 0.10300147099997048 }, "TrainerController.start_learning": { "total": 443.34080393, "count": 1, "self": 0.582613155993613, "children": { "TrainerController._reset_env": { "total": 10.248833444000013, "count": 1, "self": 10.248833444000013 }, "TrainerController.advance": { "total": 432.3907941660063, "count": 18204, "self": 0.302752746000408, "children": { "env_step": { "total": 432.0880414200059, "count": 18204, "self": 283.1051775139925, "children": { "SubprocessEnvManager._take_step": { "total": 148.68467598800004, "count": 18204, "self": 1.4550683049966437, "children": { "TorchPolicy.evaluate": { "total": 147.2296076830034, "count": 18204, "self": 33.42046859300393, "children": { "TorchPolicy.sample_actions": { "total": 113.80913908999946, "count": 18204, "self": 113.80913908999946 } } } } }, "workers": { "total": 0.29818791801335465, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 442.03076250899636, "count": 18204, "is_parallel": true, "self": 208.54623346900019, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061715280000385064, "count": 1, "is_parallel": true, "self": 0.0036278630001902457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025436649998482608, "count": 10, "is_parallel": true, "self": 0.0025436649998482608 } } }, "UnityEnvironment.step": { "total": 0.044802962000005664, "count": 1, "is_parallel": true, "self": 0.00033752100000583596, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029768199999580247, "count": 1, "is_parallel": true, "self": 0.00029768199999580247 }, "communicator.exchange": { "total": 0.04257112400000551, "count": 1, "is_parallel": true, "self": 0.04257112400000551 }, "steps_from_proto": { "total": 0.001596634999998514, "count": 1, "is_parallel": true, "self": 0.00041514999986702605, "children": { "_process_rank_one_or_two_observation": { "total": 0.001181485000131488, "count": 10, "is_parallel": true, "self": 0.001181485000131488 } } } } } } }, "UnityEnvironment.step": { "total": 233.48452903999618, "count": 18203, "is_parallel": true, "self": 8.714732948002904, "children": { "UnityEnvironment._generate_step_input": { "total": 5.032127595000134, "count": 18203, "is_parallel": true, "self": 5.032127595000134 }, "communicator.exchange": { "total": 186.86298289799828, "count": 18203, "is_parallel": true, "self": 186.86298289799828 }, "steps_from_proto": { "total": 32.87468559899486, "count": 18203, "is_parallel": true, "self": 6.862820522983327, "children": { "_process_rank_one_or_two_observation": { "total": 26.01186507601153, "count": 182030, "is_parallel": true, "self": 26.01186507601153 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.208900008961791e-05, "count": 1, "self": 4.208900008961791e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 429.4590008390138, "count": 364214, "is_parallel": true, "self": 9.652742816000625, "children": { "process_trajectory": { "total": 248.5283642450131, "count": 364214, "is_parallel": true, "self": 247.761084242013, "children": { "RLTrainer._checkpoint": { "total": 0.7672800030001099, "count": 4, "is_parallel": true, "self": 0.7672800030001099 } } }, "_update_policy": { "total": 171.27789377800008, "count": 90, "is_parallel": true, "self": 41.64418225600258, "children": { "TorchPPOOptimizer.update": { "total": 129.6337115219975, "count": 4587, "is_parallel": true, "self": 129.6337115219975 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11852107499998965, "count": 1, "self": 0.0008496159999822339, "children": { "RLTrainer._checkpoint": { "total": 0.11767145900000742, "count": 1, "self": 0.11767145900000742 } } } } } } }