{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9748460054397583, "min": 0.9748460054397583, "max": 2.8670291900634766, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9329.2763671875, "min": 9329.2763671875, "max": 29361.24609375, "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": 2.5618693828582764, "min": 0.23930050432682037, "max": 2.576982021331787, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 499.5645446777344, "min": 46.42429733276367, "max": 527.2177124023438, "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": 0.06904537622861373, "min": 0.0617535420544086, "max": 0.07926758163775245, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2761815049144549, "min": 0.2470141682176344, "max": 0.37280726668484254, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13775007843094714, "min": 0.07286990100093296, "max": 0.1490949326213084, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5510003137237885, "min": 0.29147960400373185, "max": 0.7428818099638994, "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": 24.90909090909091, "min": 3.75, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1096.0, "min": 165.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.90909090909091, "min": 3.75, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1096.0, "min": 165.0, "max": 1388.0, "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": "1679449169", "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": "1679449617" }, "total": 448.656183358, "count": 1, "self": 0.4364397769999755, "children": { "run_training.setup": { "total": 0.11282562400003826, "count": 1, "self": 0.11282562400003826 }, "TrainerController.start_learning": { "total": 448.106917957, "count": 1, "self": 0.4908389369948054, "children": { "TrainerController._reset_env": { "total": 8.199363583999968, "count": 1, "self": 8.199363583999968 }, "TrainerController.advance": { "total": 439.2880918230052, "count": 18203, "self": 0.2531225220168949, "children": { "env_step": { "total": 439.0349693009883, "count": 18203, "self": 315.9547819919875, "children": { "SubprocessEnvManager._take_step": { "total": 122.8319266989958, "count": 18203, "self": 2.3865820529942994, "children": { "TorchPolicy.evaluate": { "total": 120.4453446460015, "count": 18203, "self": 120.4453446460015 } } }, "workers": { "total": 0.24826061000499067, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 446.7143816090093, "count": 18203, "is_parallel": true, "self": 214.92658838901406, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005391566000014336, "count": 1, "is_parallel": true, "self": 0.0037132970000470777, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016782689999672584, "count": 10, "is_parallel": true, "self": 0.0016782689999672584 } } }, "UnityEnvironment.step": { "total": 0.03350999599996385, "count": 1, "is_parallel": true, "self": 0.000541368999961378, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030942099999720085, "count": 1, "is_parallel": true, "self": 0.00030942099999720085 }, "communicator.exchange": { "total": 0.03085138400001597, "count": 1, "is_parallel": true, "self": 0.03085138400001597 }, "steps_from_proto": { "total": 0.0018078219999893008, "count": 1, "is_parallel": true, "self": 0.0003739439999321803, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014338780000571205, "count": 10, "is_parallel": true, "self": 0.0014338780000571205 } } } } } } }, "UnityEnvironment.step": { "total": 231.78779321999525, "count": 18202, "is_parallel": true, "self": 9.286508675988046, "children": { "UnityEnvironment._generate_step_input": { "total": 4.994644642012815, "count": 18202, "is_parallel": true, "self": 4.994644642012815 }, "communicator.exchange": { "total": 187.43636145900211, "count": 18202, "is_parallel": true, "self": 187.43636145900211 }, "steps_from_proto": { "total": 30.070278442992276, "count": 18202, "is_parallel": true, "self": 5.830769415980228, "children": { "_process_rank_one_or_two_observation": { "total": 24.239509027012048, "count": 182020, "is_parallel": true, "self": 24.239509027012048 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012200300000131392, "count": 1, "self": 0.00012200300000131392, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 436.12988339798756, "count": 390767, "is_parallel": true, "self": 9.256091395979468, "children": { "process_trajectory": { "total": 242.1520227580076, "count": 390767, "is_parallel": true, "self": 241.4125216840077, "children": { "RLTrainer._checkpoint": { "total": 0.7395010739999179, "count": 4, "is_parallel": true, "self": 0.7395010739999179 } } }, "_update_policy": { "total": 184.72176924400048, "count": 90, "is_parallel": true, "self": 68.98621087500112, "children": { "TorchPPOOptimizer.update": { "total": 115.73555836899936, "count": 4587, "is_parallel": true, "self": 115.73555836899936 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12850161000005755, "count": 1, "self": 0.0008576640000228508, "children": { "RLTrainer._checkpoint": { "total": 0.1276439460000347, "count": 1, "self": 0.1276439460000347 } } } } } } }