{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9932991862297058, "min": 0.9932991862297058, "max": 2.864558219909668, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9505.873046875, "min": 9505.873046875, "max": 29493.4921875, "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": 12.986475944519043, "min": 0.37477657198905945, "max": 12.989788055419922, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2532.36279296875, "min": 72.70665740966797, "max": 2649.916748046875, "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": 0.06980865920537754, "min": 0.06164336879327511, "max": 0.07544110449716931, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2792346368215102, "min": 0.24657347517310044, "max": 0.3692367339293317, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19412085472368726, "min": 0.10476503922266192, "max": 0.3114837228375323, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.776483418894749, "min": 0.4190601568906477, "max": 1.4150863102838105, "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": 25.40909090909091, "min": 3.3636363636363638, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 148.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.3636363636363638, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 148.0, "max": 1396.0, "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": "1681738221", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681738669" }, "total": 447.55038256, "count": 1, "self": 0.3955383869999878, "children": { "run_training.setup": { "total": 0.11206793799999559, "count": 1, "self": 0.11206793799999559 }, "TrainerController.start_learning": { "total": 447.042776235, "count": 1, "self": 0.5365361770003574, "children": { "TrainerController._reset_env": { "total": 3.98360138299995, "count": 1, "self": 3.98360138299995 }, "TrainerController.advance": { "total": 442.3890725909997, "count": 18204, "self": 0.2587462330136532, "children": { "env_step": { "total": 442.13032635798606, "count": 18204, "self": 324.5303497379957, "children": { "SubprocessEnvManager._take_step": { "total": 117.34030073000145, "count": 18204, "self": 1.562490118000028, "children": { "TorchPolicy.evaluate": { "total": 115.77781061200142, "count": 18204, "self": 115.77781061200142 } } }, "workers": { "total": 0.25967588998889823, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 445.52969261599526, "count": 18204, "is_parallel": true, "self": 205.47261165499413, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00461542699997608, "count": 1, "is_parallel": true, "self": 0.0030291059998717174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015863210001043626, "count": 10, "is_parallel": true, "self": 0.0015863210001043626 } } }, "UnityEnvironment.step": { "total": 0.0362627079999811, "count": 1, "is_parallel": true, "self": 0.000579643000037322, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034438099999078986, "count": 1, "is_parallel": true, "self": 0.00034438099999078986 }, "communicator.exchange": { "total": 0.03340760699995826, "count": 1, "is_parallel": true, "self": 0.03340760699995826 }, "steps_from_proto": { "total": 0.0019310769999947297, "count": 1, "is_parallel": true, "self": 0.0004000249997488936, "children": { "_process_rank_one_or_two_observation": { "total": 0.001531052000245836, "count": 10, "is_parallel": true, "self": 0.001531052000245836 } } } } } } }, "UnityEnvironment.step": { "total": 240.05708096100113, "count": 18203, "is_parallel": true, "self": 9.766646478007715, "children": { "UnityEnvironment._generate_step_input": { "total": 5.273413016998802, "count": 18203, "is_parallel": true, "self": 5.273413016998802 }, "communicator.exchange": { "total": 194.13508729899092, "count": 18203, "is_parallel": true, "self": 194.13508729899092 }, "steps_from_proto": { "total": 30.881934167003692, "count": 18203, "is_parallel": true, "self": 6.010702118019367, "children": { "_process_rank_one_or_two_observation": { "total": 24.871232048984325, "count": 182030, "is_parallel": true, "self": 24.871232048984325 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010559700001522287, "count": 1, "self": 0.00010559700001522287, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 439.164791499019, "count": 388512, "is_parallel": true, "self": 9.905498664979518, "children": { "process_trajectory": { "total": 242.14108287403906, "count": 388512, "is_parallel": true, "self": 240.74100680003914, "children": { "RLTrainer._checkpoint": { "total": 1.4000760739999123, "count": 4, "is_parallel": true, "self": 1.4000760739999123 } } }, "_update_policy": { "total": 187.1182099600004, "count": 90, "is_parallel": true, "self": 67.80192644999977, "children": { "TorchPPOOptimizer.update": { "total": 119.31628351000063, "count": 4584, "is_parallel": true, "self": 119.31628351000063 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13346048699997937, "count": 1, "self": 0.00086728700000549, "children": { "RLTrainer._checkpoint": { "total": 0.13259319999997388, "count": 1, "self": 0.13259319999997388 } } } } } } }