Probabilistic guided exploration for reinforcement learning in self-organizing neural networks

• المؤلفون الرئيسيون: Wang, Peng, Zhou, Weigui Jair, Wang, Di, Tan, Ah-Hwee
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2019
• الموضوعات: Reinforcement Learning; Self-organizing Neural Networks; Engineering::Computer science and engineering
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/89871; http://hdl.handle.net/10220/49724
• المؤسسة: Nanyang Technological University

Exploration is essential in reinforcement learning, which expands the search space of potential solutions to a given problem for performance evaluations. Specifically, carefully designed exploration strategy may help the agent learn faster by taking the advantage of what it has learned previously. However, many reinforcement learning mechanisms still adopt simple exploration strategies, which select actions in a pure random manner among all the feasible actions. In this paper, we propose novel mechanisms to improve the existing knowledge-based exploration strategy based on a probabilistic guided approach to select actions. We conduct extensive experiments in a Minefield navigation simulator and the results show that our proposed probabilistic guided exploration approach significantly improves the convergence rate.