{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9728126525878906, "min": 0.9728126525878906, "max": 2.8610193729400635, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9331.21875, "min": 9331.21875, "max": 29331.169921875, "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": 12.520752906799316, "min": 0.35971611738204956, "max": 12.520752906799316, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2441.546875, "min": 69.78492736816406, "max": 2528.8564453125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07211664351309403, "min": 0.06418826253736601, "max": 0.07352564789014686, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28846657405237613, "min": 0.25710245319693487, "max": 0.36229505220670066, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19397256884943034, "min": 0.13865546397431117, "max": 0.2880750483303678, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7758902753977214, "min": 0.5546218558972447, "max": 1.372591751463273, "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": 25.136363636363637, "min": 3.8636363636363638, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 170.0, "max": 1355.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.8636363636363638, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 170.0, "max": 1355.0, "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": "1686542772", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1686543271" }, "total": 498.6544835059999, "count": 1, "self": 0.6808696560000271, "children": { "run_training.setup": { "total": 0.04630580399998507, "count": 1, "self": 0.04630580399998507 }, "TrainerController.start_learning": { "total": 497.9273080459999, "count": 1, "self": 0.6630558259994359, "children": { "TrainerController._reset_env": { "total": 2.15700523299995, "count": 1, "self": 2.15700523299995 }, "TrainerController.advance": { "total": 494.9254957010003, "count": 18221, "self": 0.2974602280136196, "children": { "env_step": { "total": 494.62803547298665, "count": 18221, "self": 402.05078272199455, "children": { "SubprocessEnvManager._take_step": { "total": 92.2317375539983, "count": 18221, "self": 2.001713037982654, "children": { "TorchPolicy.evaluate": { "total": 90.23002451601565, "count": 18221, "self": 90.23002451601565 } } }, "workers": { "total": 0.3455151969938015, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 496.06424020899544, "count": 18221, "is_parallel": true, "self": 234.4103249639967, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007127129999958015, "count": 1, "is_parallel": true, "self": 0.004553735000058623, "children": { "_process_rank_one_or_two_observation": { "total": 0.002573394999899392, "count": 10, "is_parallel": true, "self": 0.002573394999899392 } } }, "UnityEnvironment.step": { "total": 0.03955943300002218, "count": 1, "is_parallel": true, "self": 0.0006538800000726042, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004843899999968926, "count": 1, "is_parallel": true, "self": 0.0004843899999968926 }, "communicator.exchange": { "total": 0.03633769299995038, "count": 1, "is_parallel": true, "self": 0.03633769299995038 }, "steps_from_proto": { "total": 0.0020834700000023076, "count": 1, "is_parallel": true, "self": 0.000383540000029825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016999299999724826, "count": 10, "is_parallel": true, "self": 0.0016999299999724826 } } } } } } }, "UnityEnvironment.step": { "total": 261.65391524499876, "count": 18220, "is_parallel": true, "self": 11.512826265008698, "children": { "UnityEnvironment._generate_step_input": { "total": 7.19842169599292, "count": 18220, "is_parallel": true, "self": 7.19842169599292 }, "communicator.exchange": { "total": 206.66294159699214, "count": 18220, "is_parallel": true, "self": 206.66294159699214 }, "steps_from_proto": { "total": 36.279725687005, "count": 18220, "is_parallel": true, "self": 6.917109683007311, "children": { "_process_rank_one_or_two_observation": { "total": 29.362616003997687, "count": 182200, "is_parallel": true, "self": 29.362616003997687 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.186000011141005e-05, "count": 1, "self": 9.186000011141005e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 490.9327306780692, "count": 527056, "is_parallel": true, "self": 10.84116745296626, "children": { "process_trajectory": { "total": 255.347690403103, "count": 527056, "is_parallel": true, "self": 254.34960639010308, "children": { "RLTrainer._checkpoint": { "total": 0.9980840129999251, "count": 4, "is_parallel": true, "self": 0.9980840129999251 } } }, "_update_policy": { "total": 224.74387282199996, "count": 90, "is_parallel": true, "self": 67.34421901499684, "children": { "TorchPPOOptimizer.update": { "total": 157.39965380700312, "count": 4587, "is_parallel": true, "self": 157.39965380700312 } } } } } } } } }, "TrainerController._save_models": { "total": 0.18165942600012386, "count": 1, "self": 0.0010179300002164382, "children": { "RLTrainer._checkpoint": { "total": 0.18064149599990742, "count": 1, "self": 0.18064149599990742 } } } } } } }