{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408411979675293, "min": 1.408411979675293, "max": 1.4281551837921143, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69553.015625, "min": 69553.015625, "max": 76608.5234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.13935969868173, "min": 86.07867132867133, "max": 387.7674418604651, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48926.0, "min": 48757.0, "max": 50127.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49774.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49774.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.424431085586548, "min": 0.059338174760341644, "max": 2.451890707015991, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1287.3729248046875, "min": 7.5952863693237305, "max": 1393.682861328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.809314578378717, "min": 1.6654010638594627, "max": 3.997411612034833, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2022.7460411190987, "min": 213.17133617401123, "max": 2176.2550032138824, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.809314578378717, "min": 1.6654010638594627, "max": 3.997411612034833, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2022.7460411190987, "min": 213.17133617401123, "max": 2176.2550032138824, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018386733349082834, "min": 0.012944357379865323, "max": 0.020521924284791264, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0551602000472485, "min": 0.025888714759730647, "max": 0.06014692773266385, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05303875803947448, "min": 0.021732898273815714, "max": 0.061455569602549075, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15911627411842344, "min": 0.04346579654763143, "max": 0.1730850052088499, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4358988547333216e-06, "min": 3.4358988547333216e-06, "max": 0.00029536695154434986, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0307696564199964e-05, "min": 1.0307696564199964e-05, "max": 0.0008442279185906999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114526666666668, "min": 0.10114526666666668, "max": 0.19845565, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30343580000000003, "min": 0.20745890000000006, "max": 0.5814093, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.71488066666665e-05, "min": 6.71488066666665e-05, "max": 0.004922936935, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002014464199999995, "min": 0.0002014464199999995, "max": 0.014072324070000003, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677585612", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677587980" }, "total": 2367.897029796, "count": 1, "self": 0.8448904430001676, "children": { "run_training.setup": { "total": 0.11305709300000899, "count": 1, "self": 0.11305709300000899 }, "TrainerController.start_learning": { "total": 2366.93908226, "count": 1, "self": 4.0818091439377895, "children": { "TrainerController._reset_env": { "total": 10.669533195999975, "count": 1, "self": 10.669533195999975 }, "TrainerController.advance": { "total": 2352.014443214062, "count": 232301, "self": 4.4390894259677225, "children": { "env_step": { "total": 1825.272351172049, "count": 232301, "self": 1521.3790469051353, "children": { "SubprocessEnvManager._take_step": { "total": 301.15011629498775, "count": 232301, "self": 15.798634106981694, "children": { "TorchPolicy.evaluate": { "total": 285.35148218800606, "count": 222894, "self": 71.96828774800503, "children": { "TorchPolicy.sample_actions": { "total": 213.38319444000103, "count": 222894, "self": 213.38319444000103 } } } } }, "workers": { "total": 2.743187971925977, "count": 232301, "self": 0.0, "children": { "worker_root": { "total": 2358.467545791989, "count": 232301, "is_parallel": true, "self": 1125.4505193670213, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009071349999771883, "count": 1, "is_parallel": true, "self": 0.0003186909999612908, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005884440000158975, "count": 2, "is_parallel": true, "self": 0.0005884440000158975 } } }, "UnityEnvironment.step": { "total": 0.031505420000030426, "count": 1, "is_parallel": true, "self": 0.00031665500006283764, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007898899999645437, "count": 1, "is_parallel": true, "self": 0.0007898899999645437 }, "communicator.exchange": { "total": 0.029684277000001202, "count": 1, "is_parallel": true, "self": 0.029684277000001202 }, "steps_from_proto": { "total": 0.0007145980000018426, "count": 1, "is_parallel": true, "self": 0.0002216269999735232, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004929710000283194, "count": 2, "is_parallel": true, "self": 0.0004929710000283194 } } } } } } }, "UnityEnvironment.step": { "total": 1233.0170264249675, "count": 232300, "is_parallel": true, "self": 38.35520075700356, "children": { "UnityEnvironment._generate_step_input": { "total": 77.27390682790082, "count": 232300, "is_parallel": true, "self": 77.27390682790082 }, "communicator.exchange": { "total": 1026.762430628044, "count": 232300, "is_parallel": true, "self": 1026.762430628044 }, "steps_from_proto": { "total": 90.62548821201892, "count": 232300, "is_parallel": true, "self": 36.545000812048784, "children": { "_process_rank_one_or_two_observation": { "total": 54.08048739997014, "count": 464600, "is_parallel": true, "self": 54.08048739997014 } } } } } } } } } } }, "trainer_advance": { "total": 522.3030026160452, "count": 232301, "self": 6.497615079155594, "children": { "process_trajectory": { "total": 163.3382806018882, "count": 232301, "self": 162.1228746018877, "children": { "RLTrainer._checkpoint": { "total": 1.2154060000004847, "count": 10, "self": 1.2154060000004847 } } }, "_update_policy": { "total": 352.4671069350014, "count": 97, "self": 294.3582081829942, "children": { "TorchPPOOptimizer.update": { "total": 58.108898752007235, "count": 2910, "self": 58.108898752007235 } } } } } } }, "trainer_threads": { "total": 1.1430001904955134e-06, "count": 1, "self": 1.1430001904955134e-06 }, "TrainerController._save_models": { "total": 0.1732955630000106, "count": 1, "self": 0.0027563609996832383, "children": { "RLTrainer._checkpoint": { "total": 0.17053920200032735, "count": 1, "self": 0.17053920200032735 } } } } } } }