Cooperative Q-learning approach allows multiple learners to learn independently then share their Q-values among each other using a Q-value sharing strategy. A main problem with this approach is that the solutions of the learners may not converge to optimality because the optimal Q-values may not be found. Another problem is that some cooperative algorithms perform very well with single-task problems, but quite poorly with multi-task problems. This paper proposes a new cooperative Q-learning algorithm called the Bat Q-learning algorithm (BQ-learning) that implements a Q-value sharing strategy based on the Bat algorithm. The Bat algorithm is a powerful optimization algorithm that increases the possibility of finding the optimal Q-values by balancing between the exploration and exploitation of actions by tuning the parameters of the algorithm. The BQ-learning algorithm was tested using two problems: the shortest path problem (single-task problem) and the taxi problem (multi-task problem). The experimental results suggest that BQ-learning performs better than single-agent Q-learning and some well-known cooperative Q-learning algorithms.
Key words: Q-learning, Bat Algorithm, Optimization, Cooperative Reinforcement
|
