Incremental Multi-Step Q-Learning |
| |
Authors: | Peng Jing Williams Ronald J |
| |
Affiliation: | (1) College of Engineering, University of California, 92521 Riverside, CA;(2) College of Computer Science, Northeastern University, 02115 Boston, MA |
| |
Abstract: | This paper presents a novel incremental algorithm that combines Q-learning, a well-known dynamic-programming based reinforcement learning method, with the TD() return estimation process, which is typically used in actor-critic learning, another well-known dynamic-programming based reinforcement learning method. The parameter is used to distribute credit throughout sequences of actions, leading to faster learning and also helping to alleviate the non-Markovian effect of coarse state-space quantization. The resulting algorithm, Q()-learning, thus combines some of the best features of the Q-learning and actor-critic learning paradigms. The behavior of this algorithm has been demonstrated through computer simulations. |
| |
Keywords: | reinforcement learning temporal difference learning |
本文献已被 SpringerLink 等数据库收录! |
|