{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9329480528831482, "min": 0.9265595078468323, "max": 2.869509696960449, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8907.7880859375, "min": 8907.7880859375, "max": 29386.6484375, "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": 13.092435836791992, "min": 0.28902819752693176, "max": 13.092435836791992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2553.02490234375, "min": 56.071468353271484, "max": 2609.0302734375, "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": 0.06686443029235199, "min": 0.06335296537772771, "max": 0.07359331315520275, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26745772116940797, "min": 0.25341186151091083, "max": 0.3679665657760137, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1908342984377169, "min": 0.1238980646354749, "max": 0.2679464461318418, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7633371937508676, "min": 0.4955922585418996, "max": 1.2962227060514337, "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": 26.0, "min": 3.2954545454545454, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1144.0, "min": 145.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.0, "min": 3.2954545454545454, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1144.0, "min": 145.0, "max": 1401.0, "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": "1718367692", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718368165" }, "total": 473.69982002200004, "count": 1, "self": 0.43986131099973136, "children": { "run_training.setup": { "total": 0.06161612599998989, "count": 1, "self": 0.06161612599998989 }, "TrainerController.start_learning": { "total": 473.1983425850003, "count": 1, "self": 0.64334971302128, "children": { "TrainerController._reset_env": { "total": 3.2021853960000044, "count": 1, "self": 3.2021853960000044 }, "TrainerController.advance": { "total": 469.24406580497885, "count": 18201, "self": 0.317268440995349, "children": { "env_step": { "total": 468.9267973639835, "count": 18201, "self": 306.7133463549985, "children": { "SubprocessEnvManager._take_step": { "total": 161.90068791798421, "count": 18201, "self": 1.5550392809718687, "children": { "TorchPolicy.evaluate": { "total": 160.34564863701235, "count": 18201, "self": 160.34564863701235 } } }, "workers": { "total": 0.31276309100076105, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 471.8870832780142, "count": 18201, "is_parallel": true, "self": 236.0582644770211, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009056251999936649, "count": 1, "is_parallel": true, "self": 0.007394400999373829, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016618510005628195, "count": 10, "is_parallel": true, "self": 0.0016618510005628195 } } }, "UnityEnvironment.step": { "total": 0.03649030900010075, "count": 1, "is_parallel": true, "self": 0.000790018000316195, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035599099987848604, "count": 1, "is_parallel": true, "self": 0.00035599099987848604 }, "communicator.exchange": { "total": 0.032916400999965845, "count": 1, "is_parallel": true, "self": 0.032916400999965845 }, "steps_from_proto": { "total": 0.0024278989999402256, "count": 1, "is_parallel": true, "self": 0.0004333199995016912, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019945790004385344, "count": 10, "is_parallel": true, "self": 0.0019945790004385344 } } } } } } }, "UnityEnvironment.step": { "total": 235.82881880099308, "count": 18200, "is_parallel": true, "self": 10.696257846983144, "children": { "UnityEnvironment._generate_step_input": { "total": 5.538592961004497, "count": 18200, "is_parallel": true, "self": 5.538592961004497 }, "communicator.exchange": { "total": 185.26412189502685, "count": 18200, "is_parallel": true, "self": 185.26412189502685 }, "steps_from_proto": { "total": 34.32984609797859, "count": 18200, "is_parallel": true, "self": 6.657751770902678, "children": { "_process_rank_one_or_two_observation": { "total": 27.67209432707591, "count": 182000, "is_parallel": true, "self": 27.67209432707591 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014192300022841664, "count": 1, "self": 0.00014192300022841664, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.5746475970145, "count": 705068, "is_parallel": true, "self": 14.702609201066707, "children": { "process_trajectory": { "total": 256.91221596894593, "count": 705068, "is_parallel": true, "self": 256.20339395294604, "children": { "RLTrainer._checkpoint": { "total": 0.7088220159998855, "count": 4, "is_parallel": true, "self": 0.7088220159998855 } } }, "_update_policy": { "total": 191.95982242700188, "count": 90, "is_parallel": true, "self": 61.274015580998366, "children": { "TorchPPOOptimizer.update": { "total": 130.68580684600352, "count": 4587, "is_parallel": true, "self": 130.68580684600352 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10859974799996053, "count": 1, "self": 0.0009852090001913894, "children": { "RLTrainer._checkpoint": { "total": 0.10761453899976914, "count": 1, "self": 0.10761453899976914 } } } } } } }