• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.502-506
• /
• 2008

The recently proposed "Potential-based" reinforcement learning (RL) method made it possible to combine multiple learnings and expert advices as supervised knowledge within an RL framework. The effectiveness of the approach has been established by a theoretical convergence guarantee to an optimal policy. In this paper, the potential-based RL method is applied to a dynamic channel assignment (DCA) problem in a cellular networks. It is empirically shown that the potential-based RL assigns channels more efficiently than fixed channel assignment, Maxavail, and Q-learning-based DCA, and it converges to an optimal policy more rapidly than other RL algorithms, SARSA(0) and PRQ-learning.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.978-982
• /
• 2009

This paper proposes a potential-based reinforcement learning, called "RLs-CBDT", which combines multiple RL agents and case-base decision theory designed for decision making in uncertain environment as an expert knowledge in RL. We empirically show that RLs-CBDT converges to an optimal policy faster than pre-existing RL algorithms through a Tetris experiment.