{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.884098470211029, "min": 0.884098470211029, "max": 2.8652186393737793, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8441.3720703125, "min": 8441.3720703125, "max": 29342.703125, "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": 12.938516616821289, "min": 0.17400144040584564, "max": 12.938516616821289, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.0107421875, "min": 33.75627899169922, "max": 2608.77734375, "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": 0.06685131579904598, "min": 0.061574395549541805, "max": 0.07436559894624367, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2674052631961839, "min": 0.24629758219816722, "max": 0.3652608507277453, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2048176261139851, "min": 0.10134069433415253, "max": 0.2770030565121595, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8192705044559404, "min": 0.40536277733661014, "max": 1.3850152825607975, "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": 25.113636363636363, "min": 2.6363636363636362, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 116.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 2.6363636363636362, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 116.0, "max": 1407.0, "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": "1728711080", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728711767" }, "total": 686.931274091, "count": 1, "self": 0.641672758000027, "children": { "run_training.setup": { "total": 0.12246498399997563, "count": 1, "self": 0.12246498399997563 }, "TrainerController.start_learning": { "total": 686.167136349, "count": 1, "self": 1.0491958359970113, "children": { "TrainerController._reset_env": { "total": 4.10558342500002, "count": 1, "self": 4.10558342500002 }, "TrainerController.advance": { "total": 680.914601800003, "count": 18201, "self": 0.5111352830058422, "children": { "env_step": { "total": 680.4034665169971, "count": 18201, "self": 521.6593298619819, "children": { "SubprocessEnvManager._take_step": { "total": 158.2599608380039, "count": 18201, "self": 3.066866898012904, "children": { "TorchPolicy.evaluate": { "total": 155.193093939991, "count": 18201, "self": 155.193093939991 } } }, "workers": { "total": 0.4841758170113053, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 683.8248441690033, "count": 18201, "is_parallel": true, "self": 321.87547208099505, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009637507999968875, "count": 1, "is_parallel": true, "self": 0.003817350999952396, "children": { "_process_rank_one_or_two_observation": { "total": 0.005820157000016479, "count": 10, "is_parallel": true, "self": 0.005820157000016479 } } }, "UnityEnvironment.step": { "total": 0.08708025900000393, "count": 1, "is_parallel": true, "self": 0.0013256610000667024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0011813469999992776, "count": 1, "is_parallel": true, "self": 0.0011813469999992776 }, "communicator.exchange": { "total": 0.08211141199996064, "count": 1, "is_parallel": true, "self": 0.08211141199996064 }, "steps_from_proto": { "total": 0.002461838999977317, "count": 1, "is_parallel": true, "self": 0.0004672399998639776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019945990001133396, "count": 10, "is_parallel": true, "self": 0.0019945990001133396 } } } } } } }, "UnityEnvironment.step": { "total": 361.94937208800826, "count": 18200, "is_parallel": true, "self": 17.121922374001258, "children": { "UnityEnvironment._generate_step_input": { "total": 8.458464414007722, "count": 18200, "is_parallel": true, "self": 8.458464414007722 }, "communicator.exchange": { "total": 287.9277004910108, "count": 18200, "is_parallel": true, "self": 287.9277004910108 }, "steps_from_proto": { "total": 48.441284808988485, "count": 18200, "is_parallel": true, "self": 10.163704596984985, "children": { "_process_rank_one_or_two_observation": { "total": 38.2775802120035, "count": 182000, "is_parallel": true, "self": 38.2775802120035 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017848100003448053, "count": 1, "self": 0.00017848100003448053, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 673.1487769450056, "count": 834709, "is_parallel": true, "self": 21.04864633196769, "children": { "process_trajectory": { "total": 367.7958702300387, "count": 834709, "is_parallel": true, "self": 366.52130725603865, "children": { "RLTrainer._checkpoint": { "total": 1.2745629740000481, "count": 4, "is_parallel": true, "self": 1.2745629740000481 } } }, "_update_policy": { "total": 284.3042603829992, "count": 90, "is_parallel": true, "self": 79.22256421199933, "children": { "TorchPPOOptimizer.update": { "total": 205.08169617099986, "count": 4587, "is_parallel": true, "self": 205.08169617099986 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09757680699999582, "count": 1, "self": 0.0018881949999922654, "children": { "RLTrainer._checkpoint": { "total": 0.09568861200000356, "count": 1, "self": 0.09568861200000356 } } } } } } }