{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8388806581497192, "min": 0.8388806581497192, "max": 2.862894058227539, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7972.7216796875, "min": 7972.7216796875, "max": 29224.421875, "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": 13.042563438415527, "min": 0.35064059495925903, "max": 13.044713973999023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2543.2998046875, "min": 68.02427673339844, "max": 2661.12158203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07068911626839847, "min": 0.05996893992922588, "max": 0.07508209243053846, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28275646507359387, "min": 0.24428520859221275, "max": 0.37541046215269225, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2188057464857896, "min": 0.11270831406627801, "max": 0.3166458017978014, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8752229859431584, "min": 0.45083325626511206, "max": 1.4053343189697638, "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": 25.454545454545453, "min": 3.409090909090909, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 150.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.409090909090909, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 150.0, "max": 1416.0, "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": "1740358379", "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": "1740358804" }, "total": 424.281594154, "count": 1, "self": 0.5383927289999519, "children": { "run_training.setup": { "total": 0.022378684000045723, "count": 1, "self": 0.022378684000045723 }, "TrainerController.start_learning": { "total": 423.720822741, "count": 1, "self": 0.35798824100720594, "children": { "TrainerController._reset_env": { "total": 3.3971066080000583, "count": 1, "self": 3.3971066080000583 }, "TrainerController.advance": { "total": 419.8262683829929, "count": 18192, "self": 0.35594232699213535, "children": { "env_step": { "total": 295.6654730380036, "count": 18192, "self": 224.9600651499468, "children": { "SubprocessEnvManager._take_step": { "total": 70.48887399702801, "count": 18192, "self": 1.2370074839897143, "children": { "TorchPolicy.evaluate": { "total": 69.2518665130383, "count": 18192, "self": 69.2518665130383 } } }, "workers": { "total": 0.21653389102880283, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 422.0753986350045, "count": 18192, "is_parallel": true, "self": 225.24470836601415, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005778639000027397, "count": 1, "is_parallel": true, "self": 0.004121666000060031, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016569729999673655, "count": 10, "is_parallel": true, "self": 0.0016569729999673655 } } }, "UnityEnvironment.step": { "total": 0.03502715899992381, "count": 1, "is_parallel": true, "self": 0.0005639879999534969, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038523900002473965, "count": 1, "is_parallel": true, "self": 0.00038523900002473965 }, "communicator.exchange": { "total": 0.032280012999990504, "count": 1, "is_parallel": true, "self": 0.032280012999990504 }, "steps_from_proto": { "total": 0.0017979189999550726, "count": 1, "is_parallel": true, "self": 0.00035954299960394565, "children": { "_process_rank_one_or_two_observation": { "total": 0.001438376000351127, "count": 10, "is_parallel": true, "self": 0.001438376000351127 } } } } } } }, "UnityEnvironment.step": { "total": 196.83069026899034, "count": 18191, "is_parallel": true, "self": 9.523448020967635, "children": { "UnityEnvironment._generate_step_input": { "total": 5.228587256006904, "count": 18191, "is_parallel": true, "self": 5.228587256006904 }, "communicator.exchange": { "total": 151.58001755002874, "count": 18191, "is_parallel": true, "self": 151.58001755002874 }, "steps_from_proto": { "total": 30.498637441987057, "count": 18191, "is_parallel": true, "self": 5.4249187359693, "children": { "_process_rank_one_or_two_observation": { "total": 25.073718706017758, "count": 181910, "is_parallel": true, "self": 25.073718706017758 } } } } } } } } } } }, "trainer_advance": { "total": 123.80485301799717, "count": 18192, "self": 0.43428710799094006, "children": { "process_trajectory": { "total": 26.854071991004957, "count": 18192, "self": 26.26178947500489, "children": { "RLTrainer._checkpoint": { "total": 0.5922825160000684, "count": 4, "self": 0.5922825160000684 } } }, "_update_policy": { "total": 96.51649391900128, "count": 90, "self": 38.819316450000656, "children": { "TorchPPOOptimizer.update": { "total": 57.69717746900062, "count": 4587, "self": 57.69717746900062 } } } } } } }, "trainer_threads": { "total": 1.3579999631474493e-06, "count": 1, "self": 1.3579999631474493e-06 }, "TrainerController._save_models": { "total": 0.13945815099987158, "count": 1, "self": 0.001229420999834474, "children": { "RLTrainer._checkpoint": { "total": 0.1382287300000371, "count": 1, "self": 0.1382287300000371 } } } } } } }