Reinforcement Learning with Partial Parametric Model Knowledge

04/26/2023
by   Shuyuan Wang, et al.
0

We adapt reinforcement learning (RL) methods for continuous control to bridge the gap between complete ignorance and perfect knowledge of the environment. Our method, Partial Knowledge Least Squares Policy Iteration (PLSPI), takes inspiration from both model-free RL and model-based control. It uses incomplete information from a partial model and retains RL's data-driven adaption towards optimal performance. The linear quadratic regulator provides a case study; numerical experiments demonstrate the effectiveness and resulting benefits of the proposed method.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset