Reinforcement learning with Gaussian process regression using variational free energy
Reinforcement learning with Gaussian process regression using variational free energy
复制标题
DOI：
10.1515/jisys-2022-0205
复制
发表时间：
2023-01
影响因子：
3
通讯作者：
Kiseki Kameda;F. Tanaka
中科院分区：
文献类型：
--
作者：
Kiseki Kameda;F. Tanaka
摘要现有的使用高斯过程回归的强化学习算法的本质部分涉及一个复杂的在线高斯过程回归算法。我们的研究提出了在线和小批量高斯过程回归算法，这些算法更容易实现，估计也更快。在我们的算法中，高斯过程回归只通过计算两个方程来更新值函数，然后我们使用它们来构造强化学习算法。数值实验表明，该算法的性能与前人的研究结果相当。
Abstract The essential part of existing reinforcement learning algorithms that use Gaussian process regression involves a complicated online Gaussian process regression algorithm. Our study proposes online and mini-batch Gaussian process regression algorithms that are easier to implement and faster to estimate for reinforcement learning. In our algorithm, the Gaussian process regression updates the value function through only the computation of two equations, which we then use to construct reinforcement learning algorithms. Our numerical experiments show that the proposed algorithm works as well as those from previous studies.