Litcius/Paper detail

Hybrid control for combining model-based and model-free reinforcement learning

Allison Pinosky, Ian Abraham, Alexander Broad, Brenna Argall, Todd D. Murphey

2022The International Journal of Robotics Research31 citationsDOIOpen Access PDF

Abstract

We develop an approach to improve the learning capabilities of robotic systems by combining learned predictive models with experience-based state-action policy mappings. Predictive models provide an understanding of the task and the dynamics, while experience-based (model-free) policy mappings encode favorable actions that override planned actions. We refer to our approach of systematically combining model-based and model-free learning methods as hybrid learning. Our approach efficiently learns motor skills and improves the performance of predictive models and experience-based policies. Moreover, our approach enables policies (both model-based and model-free) to be updated using any off-policy reinforcement learning method. We derive a deterministic method of hybrid learning by optimally switching between learning modalities. We adapt our method to a stochastic variation that relaxes some of the key assumptions in the original derivation. Our deterministic and stochastic variations are tested on a variety of robot control benchmark tasks in simulation as well as a hardware manipulation task. We extend our approach for use with imitation learning methods, where experience is provided through demonstrations, and we test the expanded capability with a real-world pick-and-place task. The results show that our method is capable of improving the performance and sample efficiency of learning motor skills in a variety of experimental domains.

Topics & Concepts

Reinforcement learningComputer scienceBenchmark (surveying)Artificial intelligenceTask (project management)Machine learningVariety (cybernetics)Control (management)EngineeringSystems engineeringGeodesyGeographyReinforcement Learning in RoboticsRobot Manipulation and LearningMechanical Circulatory Support Devices
Hybrid control for combining model-based and model-free reinforcement learning | Litcius