{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5065417289733887, "min": 0.49549272656440735, "max": 2.813369035720825, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4858.74853515625, "min": 4858.74853515625, "max": 28718.87109375, "count": 30 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.20620059967041, "min": 2.071056842803955, "max": 13.317708015441895, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2694.06494140625, "min": 393.50079345703125, "max": 2705.673828125, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06573672673260386, "min": 0.06349465119602232, "max": 0.07748843980131342, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32868363366301934, "min": 0.2594767195506553, "max": 0.37172240696336123, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17950843812203873, "min": 0.1739506449039076, "max": 0.2768958347539107, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8975421906101937, "min": 0.6958025796156304, "max": 1.3364396822803162, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0288989903999985e-06, "min": 3.0288989903999985e-06, "max": 0.0001766088411304, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5144494951999991e-05, "min": 1.5144494951999991e-05, "max": 0.000853344215552, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1010096, "min": 0.1010096, "max": 0.1588696, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.505048, "min": 0.4119584, "max": 0.784448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 1.0908639999999999e-05, "min": 1.0908639999999999e-05, "max": 6.298264e-05, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 5.4543199999999996e-05, "min": 5.0762560000000005e-05, "max": 0.00030600320000000007, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.472727272727273, "min": 5.090909090909091, "max": 26.21818181818182, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1401.0, "min": 224.0, "max": 1442.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.472727272727273, "min": 5.090909090909091, "max": 26.21818181818182, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1401.0, "min": 224.0, "max": 1442.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1773664937", "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 --resume --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.10.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1773665602" }, "total": 665.0540399700003, "count": 1, "self": 0.6973311459996694, "children": { "run_training.setup": { "total": 0.039469952000217745, "count": 1, "self": 0.039469952000217745 }, "TrainerController.start_learning": { "total": 664.3172388720004, "count": 1, "self": 0.4871282610538401, "children": { "TrainerController._reset_env": { "total": 2.3383428580000327, "count": 1, "self": 2.3383428580000327 }, "TrainerController.advance": { "total": 658.9868647379471, "count": 27264, "self": 0.5162136149492653, "children": { "env_step": { "total": 462.7353537499994, "count": 27264, "self": 354.8981654089739, "children": { "SubprocessEnvManager._take_step": { "total": 107.53536951897786, "count": 27264, "self": 1.8760541230203671, "children": { "TorchPolicy.evaluate": { "total": 105.65931539595749, "count": 27264, "self": 105.65931539595749 } } }, "workers": { "total": 0.3018188220476077, "count": 27264, "self": 0.0, "children": { "worker_root": { "total": 658.0246860219531, "count": 27264, "is_parallel": true, "self": 344.6093568760225, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029834299994035973, "count": 1, "is_parallel": true, "self": 0.0008881549983925652, "children": { "_process_rank_one_or_two_observation": { "total": 0.002095275001011032, "count": 10, "is_parallel": true, "self": 0.002095275001011032 } } }, "UnityEnvironment.step": { "total": 0.03488423700036947, "count": 1, "is_parallel": true, "self": 0.0005924939996475587, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036805099989578594, "count": 1, "is_parallel": true, "self": 0.00036805099989578594 }, "communicator.exchange": { "total": 0.03205556900047668, "count": 1, "is_parallel": true, "self": 0.03205556900047668 }, "steps_from_proto": { "total": 0.001868123000349442, "count": 1, "is_parallel": true, "self": 0.0003917840012945817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014763389990548603, "count": 10, "is_parallel": true, "self": 0.0014763389990548603 } } } } } } }, "UnityEnvironment.step": { "total": 313.4153291459306, "count": 27263, "is_parallel": true, "self": 14.76222867101933, "children": { "UnityEnvironment._generate_step_input": { "total": 8.029466016941115, "count": 27263, "is_parallel": true, "self": 8.029466016941115 }, "communicator.exchange": { "total": 236.13212464500702, "count": 27263, "is_parallel": true, "self": 236.13212464500702 }, "steps_from_proto": { "total": 54.49150981296316, "count": 27263, "is_parallel": true, "self": 9.97395067870093, "children": { "_process_rank_one_or_two_observation": { "total": 44.51755913426223, "count": 272630, "is_parallel": true, "self": 44.51755913426223 } } } } } } } } } } }, "trainer_advance": { "total": 195.7352973729985, "count": 27264, "self": 0.6209096390075501, "children": { "process_trajectory": { "total": 52.91728896898803, "count": 27264, "self": 39.97520039498704, "children": { "RLTrainer._checkpoint": { "total": 12.94208857400099, "count": 6, "self": 12.94208857400099 } } }, "_update_policy": { "total": 142.19709876500292, "count": 136, "self": 55.1479849309535, "children": { "TorchPPOOptimizer.update": { "total": 87.04911383404942, "count": 6933, "self": 87.04911383404942 } } } } } } }, "trainer_threads": { "total": 1.0049998309114017e-06, "count": 1, "self": 1.0049998309114017e-06 }, "TrainerController._save_models": { "total": 2.5049020099995687, "count": 1, "self": 0.0008557359997212188, "children": { "RLTrainer._checkpoint": { "total": 2.5040462739998475, "count": 1, "self": 2.5040462739998475 } } } } } } }