{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9709662199020386, "min": 0.9709662199020386, "max": 2.8558804988861084, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9292.146484375, "min": 9292.146484375, "max": 29309.90234375, "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": 12.804195404052734, "min": 0.2817271053791046, "max": 12.804195404052734, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.818115234375, "min": 54.655059814453125, "max": 2583.824951171875, "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": 0.0740064225831827, "min": 0.06103239911585571, "max": 0.0740064225831827, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2960256903327308, "min": 0.25980697049956636, "max": 0.36707018341957, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21087368774939985, "min": 0.1242004631922635, "max": 0.2924331854663643, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8434947509975994, "min": 0.496801852769054, "max": 1.3305631128011965, "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": 25.25, "min": 3.4545454545454546, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 152.0, "max": 1385.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.4545454545454546, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 152.0, "max": 1385.0, "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": "1690140178", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690140661" }, "total": 482.44472819399925, "count": 1, "self": 0.7931990119996044, "children": { "run_training.setup": { "total": 0.04070701599994209, "count": 1, "self": 0.04070701599994209 }, "TrainerController.start_learning": { "total": 481.6108221659997, "count": 1, "self": 0.6006921729203896, "children": { "TrainerController._reset_env": { "total": 4.001508879000539, "count": 1, "self": 4.001508879000539 }, "TrainerController.advance": { "total": 476.78447985608, "count": 18212, "self": 0.2929638399473333, "children": { "env_step": { "total": 476.49151601613266, "count": 18212, "self": 350.1412334132201, "children": { "SubprocessEnvManager._take_step": { "total": 126.05663496795023, "count": 18212, "self": 1.8778414627722668, "children": { "TorchPolicy.evaluate": { "total": 124.17879350517796, "count": 18212, "self": 124.17879350517796 } } }, "workers": { "total": 0.29364763496232626, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 479.84479605790693, "count": 18212, "is_parallel": true, "self": 226.65659005100133, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001927867999256705, "count": 1, "is_parallel": true, "self": 0.0005796789973828709, "children": { "_process_rank_one_or_two_observation": { "total": 0.001348189001873834, "count": 10, "is_parallel": true, "self": 0.001348189001873834 } } }, "UnityEnvironment.step": { "total": 0.0501676870007941, "count": 1, "is_parallel": true, "self": 0.0003873710011248477, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030632100060756784, "count": 1, "is_parallel": true, "self": 0.00030632100060756784 }, "communicator.exchange": { "total": 0.04749740499937616, "count": 1, "is_parallel": true, "self": 0.04749740499937616 }, "steps_from_proto": { "total": 0.0019765899996855296, "count": 1, "is_parallel": true, "self": 0.00046287599980132654, "children": { "_process_rank_one_or_two_observation": { "total": 0.001513713999884203, "count": 10, "is_parallel": true, "self": 0.001513713999884203 } } } } } } }, "UnityEnvironment.step": { "total": 253.1882060069056, "count": 18211, "is_parallel": true, "self": 10.51124364575844, "children": { "UnityEnvironment._generate_step_input": { "total": 5.344316861926927, "count": 18211, "is_parallel": true, "self": 5.344316861926927 }, "communicator.exchange": { "total": 202.3594362220956, "count": 18211, "is_parallel": true, "self": 202.3594362220956 }, "steps_from_proto": { "total": 34.973209277124624, "count": 18211, "is_parallel": true, "self": 6.568538774257831, "children": { "_process_rank_one_or_two_observation": { "total": 28.404670502866793, "count": 182110, "is_parallel": true, "self": 28.404670502866793 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016383000001951586, "count": 1, "self": 0.00016383000001951586, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 473.200980504922, "count": 448428, "is_parallel": true, "self": 9.858821664987772, "children": { "process_trajectory": { "total": 257.24843308593336, "count": 448428, "is_parallel": true, "self": 255.99131642792963, "children": { "RLTrainer._checkpoint": { "total": 1.2571166580037243, "count": 4, "is_parallel": true, "self": 1.2571166580037243 } } }, "_update_policy": { "total": 206.09372575400084, "count": 90, "is_parallel": true, "self": 84.25234770501993, "children": { "TorchPPOOptimizer.update": { "total": 121.84137804898091, "count": 4584, "is_parallel": true, "self": 121.84137804898091 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2239774279987614, "count": 1, "self": 0.0011656369988486404, "children": { "RLTrainer._checkpoint": { "total": 0.22281179099991277, "count": 1, "self": 0.22281179099991277 } } } } } } }