{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.3763391971588135, "min": 2.3763391971588135, "max": 2.868990898132324, "count": 4 }, "SnowballTarget.Policy.Entropy.sum": { "value": 24440.6484375, "min": 24440.6484375, "max": 29539.130859375, "count": 4 }, "SnowballTarget.Step.mean": { "value": 39984.0, "min": 9952.0, "max": 39984.0, "count": 4 }, "SnowballTarget.Step.sum": { "value": 39984.0, "min": 9952.0, "max": 39984.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 3.880905866622925, "min": 0.3933684825897217, "max": 3.880905866622925, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 795.585693359375, "min": 76.31348419189453, "max": 795.585693359375, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06550667776963581, "min": 0.06550667776963581, "max": 0.07854923370199257, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32753338884817906, "min": 0.27325814719208485, "max": 0.34388356604590536, "count": 4 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.31115414576203215, "min": 0.12234483257063902, "max": 0.31115414576203215, "count": 4 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.5557707288101608, "min": 0.4893793302825561, "max": 1.5557707288101608, "count": 4 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.000247332017556, "min": 0.000247332017556, "max": 0.000291882002706, "count": 4 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00123666008778, "min": 0.001048728050424, "max": 0.00138516003828, "count": 4 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.182444, "min": 0.182444, "max": 0.19729400000000002, "count": 4 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.91222, "min": 0.7495760000000001, "max": 0.96172, "count": 4 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0041239556000000005, "min": 0.0041239556000000005, "max": 0.0048649706, "count": 4 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.020619778000000002, "min": 0.017483842399999998, "max": 0.023089828, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 12.290909090909091, "min": 3.6818181818181817, "max": 12.290909090909091, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 676.0, "min": 162.0, "max": 676.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 12.290909090909091, "min": 3.6818181818181817, "max": 12.290909090909091, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 676.0, "min": 162.0, "max": 676.0, "count": 4 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683548584", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683548699" }, "total": 114.76772949299999, "count": 1, "self": 0.42126242099999445, "children": { "run_training.setup": { "total": 0.046409633999985545, "count": 1, "self": 0.046409633999985545 }, "TrainerController.start_learning": { "total": 114.30005743800001, "count": 1, "self": 0.14426535899900728, "children": { "TrainerController._reset_env": { "total": 3.896796032999987, "count": 1, "self": 3.896796032999987 }, "TrainerController.advance": { "total": 109.89642357100104, "count": 4373, "self": 0.07106351800314314, "children": { "env_step": { "total": 109.8253600529979, "count": 4373, "self": 80.39210716600019, "children": { "SubprocessEnvManager._take_step": { "total": 29.365648325997768, "count": 4373, "self": 0.4912783499952411, "children": { "TorchPolicy.evaluate": { "total": 28.874369976002527, "count": 4373, "self": 28.874369976002527 } } }, "workers": { "total": 0.06760456099993917, "count": 4372, "self": 0.0, "children": { "worker_root": { "total": 113.58947412700161, "count": 4372, "is_parallel": true, "self": 53.691491769001914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00494151499998452, "count": 1, "is_parallel": true, "self": 0.0035451790001275185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013963359998570013, "count": 10, "is_parallel": true, "self": 0.0013963359998570013 } } }, "UnityEnvironment.step": { "total": 0.037555141999973785, "count": 1, "is_parallel": true, "self": 0.0005854889999454826, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033737699999392134, "count": 1, "is_parallel": true, "self": 0.00033737699999392134 }, "communicator.exchange": { "total": 0.034576963000006344, "count": 1, "is_parallel": true, "self": 0.034576963000006344 }, "steps_from_proto": { "total": 0.002055313000028036, "count": 1, "is_parallel": true, "self": 0.0004500630001302852, "children": { "_process_rank_one_or_two_observation": { "total": 0.001605249999897751, "count": 10, "is_parallel": true, "self": 0.001605249999897751 } } } } } } }, "UnityEnvironment.step": { "total": 59.897982357999695, "count": 4371, "is_parallel": true, "self": 2.359205784998778, "children": { "UnityEnvironment._generate_step_input": { "total": 1.2604879299998402, "count": 4371, "is_parallel": true, "self": 1.2604879299998402 }, "communicator.exchange": { "total": 48.284181208001485, "count": 4371, "is_parallel": true, "self": 48.284181208001485 }, "steps_from_proto": { "total": 7.9941074349995915, "count": 4371, "is_parallel": true, "self": 1.602320377002286, "children": { "_process_rank_one_or_two_observation": { "total": 6.3917870579973055, "count": 43710, "is_parallel": true, "self": 6.3917870579973055 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.440399999339206e-05, "count": 1, "self": 4.440399999339206e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 109.12033364099739, "count": 97864, "is_parallel": true, "self": 2.2756344789866034, "children": { "process_trajectory": { "total": 60.62344242801089, "count": 97864, "is_parallel": true, "self": 60.62344242801089 }, "_update_policy": { "total": 46.221256733999894, "count": 21, "is_parallel": true, "self": 17.588199666001287, "children": { "TorchPPOOptimizer.update": { "total": 28.633057067998607, "count": 1068, "is_parallel": true, "self": 28.633057067998607 } } } } } } } } }, "TrainerController._save_models": { "total": 0.36252807099998563, "count": 1, "self": 0.0011107209999750012, "children": { "RLTrainer._checkpoint": { "total": 0.36141735000001063, "count": 1, "self": 0.36141735000001063 } } } } } } }