{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8526018857955933, "min": 0.8522283434867859, "max": 2.8145687580108643, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8103.12841796875, "min": 8103.12841796875, "max": 28731.1171875, "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": 12.923022270202637, "min": 0.43106362223625183, "max": 12.94555377960205, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.9892578125, "min": 83.6263427734375, "max": 2640.89306640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06881335622165352, "min": 0.0613277409609188, "max": 0.07495847979717997, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2752534248866141, "min": 0.2453109638436752, "max": 0.3679215241821058, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2391781419807789, "min": 0.14892128972660784, "max": 0.29740313040275196, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9567125679231157, "min": 0.5956851589064314, "max": 1.4870156520137598, "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.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.Environment.CumulativeReward.mean": { "value": 24.886363636363637, "min": 3.977272727272727, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 175.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 3.977272727272727, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 175.0, "max": 1394.0, "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": "1743204617", "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 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743205053" }, "total": 436.2425297290001, "count": 1, "self": 0.43654808000064804, "children": { "run_training.setup": { "total": 0.030586727999889263, "count": 1, "self": 0.030586727999889263 }, "TrainerController.start_learning": { "total": 435.7753949209996, "count": 1, "self": 0.34826147196099555, "children": { "TrainerController._reset_env": { "total": 3.253544866000084, "count": 1, "self": 3.253544866000084 }, "TrainerController.advance": { "total": 432.0821482160386, "count": 18192, "self": 0.36820722999118516, "children": { "env_step": { "total": 305.2953305480123, "count": 18192, "self": 232.8615772271005, "children": { "SubprocessEnvManager._take_step": { "total": 72.21775308596034, "count": 18192, "self": 1.2504656619657908, "children": { "TorchPolicy.evaluate": { "total": 70.96728742399455, "count": 18192, "self": 70.96728742399455 } } }, "workers": { "total": 0.2160002349514798, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 434.3054660040011, "count": 18192, "is_parallel": true, "self": 229.98657303703294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00614755900005548, "count": 1, "is_parallel": true, "self": 0.0045295519998944656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016180070001610147, "count": 10, "is_parallel": true, "self": 0.0016180070001610147 } } }, "UnityEnvironment.step": { "total": 0.06850439099980576, "count": 1, "is_parallel": true, "self": 0.0005631449994325521, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000384721000045829, "count": 1, "is_parallel": true, "self": 0.000384721000045829 }, "communicator.exchange": { "total": 0.06585304999998698, "count": 1, "is_parallel": true, "self": 0.06585304999998698 }, "steps_from_proto": { "total": 0.0017034750003404042, "count": 1, "is_parallel": true, "self": 0.000314612001147907, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013888629991924972, "count": 10, "is_parallel": true, "self": 0.0013888629991924972 } } } } } } }, "UnityEnvironment.step": { "total": 204.31889296696818, "count": 18191, "is_parallel": true, "self": 9.977465099965684, "children": { "UnityEnvironment._generate_step_input": { "total": 5.439234792019306, "count": 18191, "is_parallel": true, "self": 5.439234792019306 }, "communicator.exchange": { "total": 157.23990267198542, "count": 18191, "is_parallel": true, "self": 157.23990267198542 }, "steps_from_proto": { "total": 31.66229040299777, "count": 18191, "is_parallel": true, "self": 5.580524332094683, "children": { "_process_rank_one_or_two_observation": { "total": 26.081766070903086, "count": 181910, "is_parallel": true, "self": 26.081766070903086 } } } } } } } } } } }, "trainer_advance": { "total": 126.4186104380351, "count": 18192, "self": 0.43682011602140847, "children": { "process_trajectory": { "total": 27.707362547013872, "count": 18192, "self": 27.244705332014746, "children": { "RLTrainer._checkpoint": { "total": 0.46265721499912615, "count": 4, "self": 0.46265721499912615 } } }, "_update_policy": { "total": 98.27442777499982, "count": 90, "self": 39.125339588998486, "children": { "TorchPPOOptimizer.update": { "total": 59.149088186001336, "count": 4587, "self": 59.149088186001336 } } } } } } }, "trainer_threads": { "total": 9.840000529948156e-07, "count": 1, "self": 9.840000529948156e-07 }, "TrainerController._save_models": { "total": 0.09143938299985166, "count": 1, "self": 0.0010093219998452696, "children": { "RLTrainer._checkpoint": { "total": 0.09043006100000639, "count": 1, "self": 0.09043006100000639 } } } } } } }