Improved decision making in multiagent system for diagnostic application using cooperative learning algorithms

Cooperative nature in multiagent system inculcates more understanding and data by sharing the resources. So cooperation in a multiagent system gives higher efficiency and faster learning compared to that of single learning. However, there are some challenges in front of learning in a cooperative manner in the multiagent system that needs to pay attention. Making effective cooperative decisions that correctly and efficiently solve interacting problems requires agents to closely cooperate their actions during problem-solving. So various issues related with cooperative machine learning are implemented. Reinforcement learning is mainly implemented with game theory and robot applications. Paper gives the new approach for reinforcement learning methods applied to the diagnostic application. The novelty of the approach lies in the amalgamation two methods i.e. weighted strategy sharing with expertness parameter that enhances the learning performance. Weighted strategy method is implemented with Sarsa (λ), Q(λ) and Sarsa learning for cooperation between the agents that was not implemented previously. Cooperative learning model with individual and cooperative learning is given in this paper. Weighted Strategy Sharing algorithms calculate the weight of each Q table based upon expertness value. Variation of WSS method with Q-learning and Sarsa learning is implemented in this paper. The paper shows implementation results and performance comparison of Weighted Strategy Sharing with Q-learning, Q(λ), Sarsa learning and Sarsa(λ) algorithms. © 2017, Bharati Vidyapeeth's Institute of Computer Applications and Management.