{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.144112229347229, "min": 1.144112229347229, "max": 2.8595616817474365, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10923.9833984375, "min": 10923.9833984375, "max": 29253.31640625, "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": 67.17129516601562, "min": 0.384268581867218, "max": 67.17129516601562, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 13098.40234375, "min": 74.54810333251953, "max": 13098.40234375, "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": 0.07276558252530829, "min": 0.06539689174507443, "max": 0.07383648079549483, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29106233010123317, "min": 0.2615875669802977, "max": 0.36579887443561654, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 1.0837052799030846, "min": 0.16939975945598573, "max": 1.0837052799030846, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.3348211196123385, "min": 0.6775990378239429, "max": 4.337784995050991, "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": 23.84090909090909, "min": 3.5, "max": 24.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1049.0, "min": 154.0, "max": 1325.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.84090909090909, "min": 3.5, "max": 24.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1049.0, "min": 154.0, "max": 1325.0, "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": "1673690927", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --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": "1673691403" }, "total": 475.6290974860001, "count": 1, "self": 0.42382411100015815, "children": { "run_training.setup": { "total": 0.11316289699993831, "count": 1, "self": 0.11316289699993831 }, "TrainerController.start_learning": { "total": 475.092110478, "count": 1, "self": 0.6427437140075654, "children": { "TrainerController._reset_env": { "total": 6.599761932999854, "count": 1, "self": 6.599761932999854 }, "TrainerController.advance": { "total": 467.72064943399255, "count": 18201, "self": 0.32319268497872145, "children": { "env_step": { "total": 467.3974567490138, "count": 18201, "self": 307.8909660900108, "children": { "SubprocessEnvManager._take_step": { "total": 159.17937152998434, "count": 18201, "self": 1.6009476850042574, "children": { "TorchPolicy.evaluate": { "total": 157.57842384498008, "count": 18201, "self": 36.672724696971954, "children": { "TorchPolicy.sample_actions": { "total": 120.90569914800813, "count": 18201, "self": 120.90569914800813 } } } } }, "workers": { "total": 0.32711912901868345, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 473.47237303098063, "count": 18201, "is_parallel": true, "self": 221.32741418498745, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029300670000793616, "count": 1, "is_parallel": true, "self": 0.0008891459999631479, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020409210001162137, "count": 10, "is_parallel": true, "self": 0.0020409210001162137 } } }, "UnityEnvironment.step": { "total": 0.03490204100012306, "count": 1, "is_parallel": true, "self": 0.00045238900020194706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002990129999034252, "count": 1, "is_parallel": true, "self": 0.0002990129999034252 }, "communicator.exchange": { "total": 0.03260027400006038, "count": 1, "is_parallel": true, "self": 0.03260027400006038 }, "steps_from_proto": { "total": 0.00155036499995731, "count": 1, "is_parallel": true, "self": 0.0004279359995962295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011224290003610804, "count": 10, "is_parallel": true, "self": 0.0011224290003610804 } } } } } } }, "UnityEnvironment.step": { "total": 252.1449588459932, "count": 18200, "is_parallel": true, "self": 9.5462258999994, "children": { "UnityEnvironment._generate_step_input": { "total": 5.535015773978785, "count": 18200, "is_parallel": true, "self": 5.535015773978785 }, "communicator.exchange": { "total": 200.17954403402405, "count": 18200, "is_parallel": true, "self": 200.17954403402405 }, "steps_from_proto": { "total": 36.884173137990956, "count": 18200, "is_parallel": true, "self": 7.916752958025199, "children": { "_process_rank_one_or_two_observation": { "total": 28.967420179965757, "count": 182000, "is_parallel": true, "self": 28.967420179965757 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.445100012162584e-05, "count": 1, "self": 4.445100012162584e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.4002171850518, "count": 399893, "is_parallel": true, "self": 10.305474570116075, "children": { "process_trajectory": { "total": 266.7627234199351, "count": 399893, "is_parallel": true, "self": 265.9526621649352, "children": { "RLTrainer._checkpoint": { "total": 0.8100612549999369, "count": 4, "is_parallel": true, "self": 0.8100612549999369 } } }, "_update_policy": { "total": 187.3320191950006, "count": 90, "is_parallel": true, "self": 47.53873108199832, "children": { "TorchPPOOptimizer.update": { "total": 139.7932881130023, "count": 4584, "is_parallel": true, "self": 139.7932881130023 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12891094599990538, "count": 1, "self": 0.0009705309998935263, "children": { "RLTrainer._checkpoint": { "total": 0.12794041500001185, "count": 1, "self": 0.12794041500001185 } } } } } } }