{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8785366415977478, "min": 0.8580255508422852, "max": 2.854755401611328, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8349.6123046875, "min": 8233.0712890625, "max": 29141.34375, "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": 13.207103729248047, "min": 0.43646925687789917, "max": 13.226140975952148, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2575.38525390625, "min": 84.67503356933594, "max": 2698.1328125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.08092386588039374, "min": 0.06000091781007701, "max": 0.08092386588039374, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32369546352157497, "min": 0.24000367124030805, "max": 0.3750996850316833, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18120505752078458, "min": 0.12068287526284727, "max": 0.28513952119677677, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7248202300831383, "min": 0.48273150105138907, "max": 1.4256976059838837, "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": 25.90909090909091, "min": 3.5681818181818183, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 157.0, "max": 1432.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.5681818181818183, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 157.0, "max": 1432.0, "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": "1752839723", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752840139" }, "total": 416.161790816, "count": 1, "self": 0.43814168500000505, "children": { "run_training.setup": { "total": 0.023200046000056318, "count": 1, "self": 0.023200046000056318 }, "TrainerController.start_learning": { "total": 415.70044908499995, "count": 1, "self": 0.32766253402542134, "children": { "TrainerController._reset_env": { "total": 3.541665944999977, "count": 1, "self": 3.541665944999977 }, "TrainerController.advance": { "total": 411.72429745897443, "count": 18192, "self": 0.3647207119764744, "children": { "env_step": { "total": 295.2316270099941, "count": 18192, "self": 226.50798088000545, "children": { "SubprocessEnvManager._take_step": { "total": 68.52276570500271, "count": 18192, "self": 1.235591522984464, "children": { "TorchPolicy.evaluate": { "total": 67.28717418201825, "count": 18192, "self": 67.28717418201825 } } }, "workers": { "total": 0.2008804249859395, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 414.23594218297944, "count": 18192, "is_parallel": true, "self": 215.55324131198108, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004746748000002299, "count": 1, "is_parallel": true, "self": 0.0032543459998350954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014924020001672034, "count": 10, "is_parallel": true, "self": 0.0014924020001672034 } } }, "UnityEnvironment.step": { "total": 0.03591601800007993, "count": 1, "is_parallel": true, "self": 0.0006211730001268734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003779380000423771, "count": 1, "is_parallel": true, "self": 0.0003779380000423771 }, "communicator.exchange": { "total": 0.0329559969999309, "count": 1, "is_parallel": true, "self": 0.0329559969999309 }, "steps_from_proto": { "total": 0.0019609099999797763, "count": 1, "is_parallel": true, "self": 0.00044718799983911595, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015137220001406604, "count": 10, "is_parallel": true, "self": 0.0015137220001406604 } } } } } } }, "UnityEnvironment.step": { "total": 198.68270087099836, "count": 18191, "is_parallel": true, "self": 9.655328227012092, "children": { "UnityEnvironment._generate_step_input": { "total": 5.380452866998439, "count": 18191, "is_parallel": true, "self": 5.380452866998439 }, "communicator.exchange": { "total": 152.36494218497376, "count": 18191, "is_parallel": true, "self": 152.36494218497376 }, "steps_from_proto": { "total": 31.281977592014073, "count": 18191, "is_parallel": true, "self": 5.523854326017613, "children": { "_process_rank_one_or_two_observation": { "total": 25.75812326599646, "count": 181910, "is_parallel": true, "self": 25.75812326599646 } } } } } } } } } } }, "trainer_advance": { "total": 116.12794973700386, "count": 18192, "self": 0.40417895599819076, "children": { "process_trajectory": { "total": 25.585748327004808, "count": 18192, "self": 25.035101023004586, "children": { "RLTrainer._checkpoint": { "total": 0.550647304000222, "count": 4, "self": 0.550647304000222 } } }, "_update_policy": { "total": 90.13802245400086, "count": 90, "self": 37.46624316000407, "children": { "TorchPPOOptimizer.update": { "total": 52.67177929399679, "count": 4587, "self": 52.67177929399679 } } } } } } }, "trainer_threads": { "total": 1.3760000001639128e-06, "count": 1, "self": 1.3760000001639128e-06 }, "TrainerController._save_models": { "total": 0.10682177100011359, "count": 1, "self": 0.0008076000001437933, "children": { "RLTrainer._checkpoint": { "total": 0.10601417099996979, "count": 1, "self": 0.10601417099996979 } } } } } } }