{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9368424415588379, "min": 0.9368424415588379, "max": 2.8742334842681885, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8944.9716796875, "min": 8944.9716796875, "max": 29466.640625, "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": 13.008551597595215, "min": 0.3574753701686859, "max": 13.008551597595215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2536.66748046875, "min": 69.3502197265625, "max": 2645.86865234375, "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": 0.06798615471580335, "min": 0.060949840624908026, "max": 0.07520110468231353, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2719446188632134, "min": 0.24896551807942874, "max": 0.36781489874713363, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20708608517751975, "min": 0.12006089207602154, "max": 0.28805459568313524, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.828344340710079, "min": 0.48024356830408615, "max": 1.3505341249938105, "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": 25.15909090909091, "min": 3.272727272727273, "max": 25.8, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 144.0, "max": 1419.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.272727272727273, "max": 25.8, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 144.0, "max": 1419.0, "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": "1696152145", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1696152617" }, "total": 472.37066871099995, "count": 1, "self": 0.43724204899996266, "children": { "run_training.setup": { "total": 0.06804689899996674, "count": 1, "self": 0.06804689899996674 }, "TrainerController.start_learning": { "total": 471.865379763, "count": 1, "self": 0.5328427359999068, "children": { "TrainerController._reset_env": { "total": 5.206065463000016, "count": 1, "self": 5.206065463000016 }, "TrainerController.advance": { "total": 465.97143644300013, "count": 18201, "self": 0.2853177629955894, "children": { "env_step": { "total": 465.68611868000454, "count": 18201, "self": 339.11796939299853, "children": { "SubprocessEnvManager._take_step": { "total": 126.28892221800436, "count": 18201, "self": 1.8588902850171962, "children": { "TorchPolicy.evaluate": { "total": 124.43003193298716, "count": 18201, "self": 124.43003193298716 } } }, "workers": { "total": 0.2792270690016494, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 470.3779649899947, "count": 18201, "is_parallel": true, "self": 222.8587578849906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006435666000015772, "count": 1, "is_parallel": true, "self": 0.00397108799995749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024645780000582818, "count": 10, "is_parallel": true, "self": 0.0024645780000582818 } } }, "UnityEnvironment.step": { "total": 0.05216335200003641, "count": 1, "is_parallel": true, "self": 0.0006374190000428825, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042223700000931785, "count": 1, "is_parallel": true, "self": 0.00042223700000931785 }, "communicator.exchange": { "total": 0.04755652899996221, "count": 1, "is_parallel": true, "self": 0.04755652899996221 }, "steps_from_proto": { "total": 0.003547167000022, "count": 1, "is_parallel": true, "self": 0.0006285120000484312, "children": { "_process_rank_one_or_two_observation": { "total": 0.002918654999973569, "count": 10, "is_parallel": true, "self": 0.002918654999973569 } } } } } } }, "UnityEnvironment.step": { "total": 247.5192071050041, "count": 18200, "is_parallel": true, "self": 10.583323179997308, "children": { "UnityEnvironment._generate_step_input": { "total": 5.358911577007007, "count": 18200, "is_parallel": true, "self": 5.358911577007007 }, "communicator.exchange": { "total": 195.65833841500313, "count": 18200, "is_parallel": true, "self": 195.65833841500313 }, "steps_from_proto": { "total": 35.91863393299667, "count": 18200, "is_parallel": true, "self": 6.489177969983643, "children": { "_process_rank_one_or_two_observation": { "total": 29.429455963013027, "count": 182000, "is_parallel": true, "self": 29.429455963013027 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012039499995353253, "count": 1, "self": 0.00012039499995353253, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 462.4715848830181, "count": 437359, "is_parallel": true, "self": 9.628802526012066, "children": { "process_trajectory": { "total": 249.76731195600632, "count": 437359, "is_parallel": true, "self": 248.54796226900635, "children": { "RLTrainer._checkpoint": { "total": 1.2193496869999763, "count": 4, "is_parallel": true, "self": 1.2193496869999763 } } }, "_update_policy": { "total": 203.07547040099973, "count": 90, "is_parallel": true, "self": 83.47007144099717, "children": { "TorchPPOOptimizer.update": { "total": 119.60539896000256, "count": 4584, "is_parallel": true, "self": 119.60539896000256 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15491472600001543, "count": 1, "self": 0.0009684540000307607, "children": { "RLTrainer._checkpoint": { "total": 0.15394627199998467, "count": 1, "self": 0.15394627199998467 } } } } } } }