{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7472427487373352, "min": 0.7472427487373352, "max": 2.8466687202453613, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7101.794921875, "min": 7101.794921875, "max": 29058.794921875, "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": 13.034502983093262, "min": 0.4047476351261139, "max": 13.034502983093262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2541.72802734375, "min": 78.52104187011719, "max": 2647.320556640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07028807099171294, "min": 0.06143335041084428, "max": 0.07498490621433387, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28115228396685177, "min": 0.24976903849749885, "max": 0.36007239407398645, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2004097961985013, "min": 0.11265492614121268, "max": 0.3074605271366297, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8016391847940052, "min": 0.45061970456485073, "max": 1.2921357403198879, "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.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": 25.65909090909091, "min": 3.159090909090909, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 139.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 3.159090909090909, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 139.0, "max": 1407.0, "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": "1742670304", "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": "1742670673" }, "total": 369.70829166, "count": 1, "self": 0.32213711400004286, "children": { "run_training.setup": { "total": 0.02101992699999755, "count": 1, "self": 0.02101992699999755 }, "TrainerController.start_learning": { "total": 369.36513461899995, "count": 1, "self": 0.2909297670162232, "children": { "TrainerController._reset_env": { "total": 2.315861294000115, "count": 1, "self": 2.315861294000115 }, "TrainerController.advance": { "total": 366.6738311919837, "count": 18192, "self": 0.2998043939614945, "children": { "env_step": { "total": 260.06048464501396, "count": 18192, "self": 196.07281211401846, "children": { "SubprocessEnvManager._take_step": { "total": 63.80359809500965, "count": 18192, "self": 1.0954919220134798, "children": { "TorchPolicy.evaluate": { "total": 62.70810617299617, "count": 18192, "self": 62.70810617299617 } } }, "workers": { "total": 0.18407443598584905, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 368.5819574410011, "count": 18192, "is_parallel": true, "self": 195.14984091099382, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022621670000262384, "count": 1, "is_parallel": true, "self": 0.0007331179997436266, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015290490002826118, "count": 10, "is_parallel": true, "self": 0.0015290490002826118 } } }, "UnityEnvironment.step": { "total": 0.027562936999856902, "count": 1, "is_parallel": true, "self": 0.00032454300003337266, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023592899992763705, "count": 1, "is_parallel": true, "self": 0.00023592899992763705 }, "communicator.exchange": { "total": 0.025684363999971538, "count": 1, "is_parallel": true, "self": 0.025684363999971538 }, "steps_from_proto": { "total": 0.0013181009999243543, "count": 1, "is_parallel": true, "self": 0.00028822999979638553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010298710001279687, "count": 10, "is_parallel": true, "self": 0.0010298710001279687 } } } } } } }, "UnityEnvironment.step": { "total": 173.4321165300073, "count": 18191, "is_parallel": true, "self": 6.868564056994046, "children": { "UnityEnvironment._generate_step_input": { "total": 3.772518856994793, "count": 18191, "is_parallel": true, "self": 3.772518856994793 }, "communicator.exchange": { "total": 139.8703094639966, "count": 18191, "is_parallel": true, "self": 139.8703094639966 }, "steps_from_proto": { "total": 22.920724152021876, "count": 18191, "is_parallel": true, "self": 4.308922888986444, "children": { "_process_rank_one_or_two_observation": { "total": 18.61180126303543, "count": 181910, "is_parallel": true, "self": 18.61180126303543 } } } } } } } } } } }, "trainer_advance": { "total": 106.31354215300826, "count": 18192, "self": 0.36014823699929366, "children": { "process_trajectory": { "total": 23.35787457300944, "count": 18192, "self": 22.959323197009553, "children": { "RLTrainer._checkpoint": { "total": 0.39855137599988666, "count": 4, "self": 0.39855137599988666 } } }, "_update_policy": { "total": 82.59551934299952, "count": 90, "self": 31.741492300003983, "children": { "TorchPPOOptimizer.update": { "total": 50.85402704299554, "count": 4587, "self": 50.85402704299554 } } } } } } }, "trainer_threads": { "total": 1.0090000159834744e-06, "count": 1, "self": 1.0090000159834744e-06 }, "TrainerController._save_models": { "total": 0.08451135699988299, "count": 1, "self": 0.0008835089997774048, "children": { "RLTrainer._checkpoint": { "total": 0.08362784800010559, "count": 1, "self": 0.08362784800010559 } } } } } } }