{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9193297028541565, "min": 0.9193297028541565, "max": 2.8362698554992676, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8737.3095703125, "min": 8737.3095703125, "max": 28952.642578125, "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": 12.652316093444824, "min": 0.3466540575027466, "max": 12.652316093444824, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2467.20166015625, "min": 67.25088500976562, "max": 2569.09716796875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07488831861558662, "min": 0.060489251078394646, "max": 0.07488831861558662, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2995532744623465, "min": 0.24195700431357858, "max": 0.3575589133143498, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21986493439066646, "min": 0.11435639866235137, "max": 0.2971107342663933, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8794597375626658, "min": 0.45742559464940546, "max": 1.4855536713319664, "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": 24.84090909090909, "min": 2.8181818181818183, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 124.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 2.8181818181818183, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 124.0, "max": 1374.0, "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": "1777366519", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1777367000" }, "total": 480.47554868199995, "count": 1, "self": 0.4331256669998993, "children": { "run_training.setup": { "total": 0.02813055000001441, "count": 1, "self": 0.02813055000001441 }, "TrainerController.start_learning": { "total": 480.01429246500004, "count": 1, "self": 0.388495285988256, "children": { "TrainerController._reset_env": { "total": 2.9557469000000083, "count": 1, "self": 2.9557469000000083 }, "TrainerController.advance": { "total": 476.5864013260118, "count": 18192, "self": 0.4239169430095444, "children": { "env_step": { "total": 349.000718456001, "count": 18192, "self": 272.90812899098637, "children": { "SubprocessEnvManager._take_step": { "total": 75.85823870300067, "count": 18192, "self": 1.3817618440042452, "children": { "TorchPolicy.evaluate": { "total": 74.47647685899642, "count": 18192, "self": 74.47647685899642 } } }, "workers": { "total": 0.23435076201394622, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 478.0649742570049, "count": 18192, "is_parallel": true, "self": 238.00287316302115, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004708364999942205, "count": 1, "is_parallel": true, "self": 0.0030191839999815784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016891809999606267, "count": 10, "is_parallel": true, "self": 0.0016891809999606267 } } }, "UnityEnvironment.step": { "total": 0.039902076999965175, "count": 1, "is_parallel": true, "self": 0.0006106660000568809, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004121270000041477, "count": 1, "is_parallel": true, "self": 0.0004121270000041477 }, "communicator.exchange": { "total": 0.03656001199999537, "count": 1, "is_parallel": true, "self": 0.03656001199999537 }, "steps_from_proto": { "total": 0.0023192719999087785, "count": 1, "is_parallel": true, "self": 0.0004045819998736988, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019146900000350797, "count": 10, "is_parallel": true, "self": 0.0019146900000350797 } } } } } } }, "UnityEnvironment.step": { "total": 240.06210109398376, "count": 18191, "is_parallel": true, "self": 11.163368892011249, "children": { "UnityEnvironment._generate_step_input": { "total": 6.135018399977071, "count": 18191, "is_parallel": true, "self": 6.135018399977071 }, "communicator.exchange": { "total": 182.03397949400266, "count": 18191, "is_parallel": true, "self": 182.03397949400266 }, "steps_from_proto": { "total": 40.72973430799277, "count": 18191, "is_parallel": true, "self": 6.989407497999764, "children": { "_process_rank_one_or_two_observation": { "total": 33.74032680999301, "count": 181910, "is_parallel": true, "self": 33.74032680999301 } } } } } } } } } } }, "trainer_advance": { "total": 127.16176592700128, "count": 18192, "self": 0.4795289700084595, "children": { "process_trajectory": { "total": 28.552618311993342, "count": 18192, "self": 28.081484801993042, "children": { "RLTrainer._checkpoint": { "total": 0.4711335100002998, "count": 4, "self": 0.4711335100002998 } } }, "_update_policy": { "total": 98.12961864499948, "count": 90, "self": 40.30036602400219, "children": { "TorchPPOOptimizer.update": { "total": 57.829252620997295, "count": 4587, "self": 57.829252620997295 } } } } } } }, "trainer_threads": { "total": 1.742999984344351e-06, "count": 1, "self": 1.742999984344351e-06 }, "TrainerController._save_models": { "total": 0.08364720999998099, "count": 1, "self": 0.0007367729999714356, "children": { "RLTrainer._checkpoint": { "total": 0.08291043700000955, "count": 1, "self": 0.08291043700000955 } } } } } } }