TY - JOUR AU - Konidaris, George AU - Osentoski, Sarah AU - Thomas, Philip PY - 2011/08/04 Y2 - 2024/03/28 TI - Value Function Approximation in Reinforcement Learning Using the Fourier Basis JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 25 IS - 1 SE - AAAI Technical Track: Machine Learning DO - 10.1609/aaai.v25i1.7903 UR - https://ojs.aaai.org/index.php/AAAI/article/view/7903 SP - 380-385 AB - <p> We describe the Fourier basis, a linear value function approximation scheme based on the Fourier series. We empirically demonstrate that it performs well compared to radial basis functions and the polynomial basis, the two most popular fixed bases for linear value function approximation, and is competitive with learned proto-value functions. </p> ER -