{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1322945356369019, "min": 1.1322945356369019, "max": 2.8558342456817627, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10848.513671875, "min": 10848.513671875, "max": 29278.01171875, "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": 11.974501609802246, "min": 0.4376535713672638, "max": 11.974501609802246, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2335.02783203125, "min": 84.90479278564453, "max": 2398.787841796875, "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": 0.06677463126800598, "min": 0.060284501939100205, "max": 0.07628564718784307, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2670985250720239, "min": 0.24113800775640082, "max": 0.3767743916724416, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.211860485009703, "min": 0.10933664314535575, "max": 0.2908311834522322, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.847441940038812, "min": 0.437346572581423, "max": 1.454155917261161, "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": 23.954545454545453, "min": 3.272727272727273, "max": 23.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1054.0, "min": 144.0, "max": 1291.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.954545454545453, "min": 3.272727272727273, "max": 23.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1054.0, "min": 144.0, "max": 1291.0, "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": "1679674826", "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": "1679675284" }, "total": 458.05725936299996, "count": 1, "self": 0.38120635099983247, "children": { "run_training.setup": { "total": 0.10415301900002305, "count": 1, "self": 0.10415301900002305 }, "TrainerController.start_learning": { "total": 457.5718999930001, "count": 1, "self": 0.531236218999652, "children": { "TrainerController._reset_env": { "total": 9.789148635999936, "count": 1, "self": 9.789148635999936 }, "TrainerController.advance": { "total": 447.1038243300004, "count": 18205, "self": 0.27114537599527466, "children": { "env_step": { "total": 446.83267895400513, "count": 18205, "self": 323.02302907798696, "children": { "SubprocessEnvManager._take_step": { "total": 123.54844523900294, "count": 18205, "self": 2.042846366021763, "children": { "TorchPolicy.evaluate": { "total": 121.50559887298118, "count": 18205, "self": 121.50559887298118 } } }, "workers": { "total": 0.26120463701522567, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 456.05685000499545, "count": 18205, "is_parallel": true, "self": 216.83978242399007, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004980694999972002, "count": 1, "is_parallel": true, "self": 0.003484442000285526, "children": { "_process_rank_one_or_two_observation": { "total": 0.001496252999686476, "count": 10, "is_parallel": true, "self": 0.001496252999686476 } } }, "UnityEnvironment.step": { "total": 0.043805836999922576, "count": 1, "is_parallel": true, "self": 0.000545662000035918, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002816219999886016, "count": 1, "is_parallel": true, "self": 0.0002816219999886016 }, "communicator.exchange": { "total": 0.04110232799996538, "count": 1, "is_parallel": true, "self": 0.04110232799996538 }, "steps_from_proto": { "total": 0.0018762249999326741, "count": 1, "is_parallel": true, "self": 0.00038694599959399056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014892790003386835, "count": 10, "is_parallel": true, "self": 0.0014892790003386835 } } } } } } }, "UnityEnvironment.step": { "total": 239.21706758100538, "count": 18204, "is_parallel": true, "self": 9.495424125030581, "children": { "UnityEnvironment._generate_step_input": { "total": 5.198842343005708, "count": 18204, "is_parallel": true, "self": 5.198842343005708 }, "communicator.exchange": { "total": 193.7265980409777, "count": 18204, "is_parallel": true, "self": 193.7265980409777 }, "steps_from_proto": { "total": 30.796203071991386, "count": 18204, "is_parallel": true, "self": 6.041371538006274, "children": { "_process_rank_one_or_two_observation": { "total": 24.75483153398511, "count": 182040, "is_parallel": true, "self": 24.75483153398511 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001591729999290692, "count": 1, "self": 0.0001591729999290692, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.8729001199465, "count": 407662, "is_parallel": true, "self": 9.504065423941142, "children": { "process_trajectory": { "total": 246.4948647380046, "count": 407662, "is_parallel": true, "self": 245.60826828500456, "children": { "RLTrainer._checkpoint": { "total": 0.8865964530000383, "count": 4, "is_parallel": true, "self": 0.8865964530000383 } } }, "_update_policy": { "total": 187.87396995800077, "count": 90, "is_parallel": true, "self": 70.26837018799858, "children": { "TorchPPOOptimizer.update": { "total": 117.60559977000219, "count": 4587, "is_parallel": true, "self": 117.60559977000219 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14753163500017763, "count": 1, "self": 0.0009338040001694026, "children": { "RLTrainer._checkpoint": { "total": 0.14659783100000823, "count": 1, "self": 0.14659783100000823 } } } } } } }