Enhanced Cooperative Multi-agent Learning Algorithms (ECMLA) using Reinforcement Learning

Cooperation in agent learning (CL) is understood in a multiagent environment. The agents are competent for learning from both other agents' knowledge and expertise and their own experience. This paper proposes a new move toward Enhanced Cooperative Multi-agent Learning Algorithms (ECMLA) using reinforcement learning methods. The paper shows the performance comparison between multi-agent learning algorithms and enhanced cooperative multi-agent learning algorithms using reinforcement learning methods. We explore a new approach for dynamic products availability in a three retailer shops in the market. Retailers can cooperate with each other and can get benefit from cooperative information by their own policies that accurately represent their goals and interests. The retailers are the learning agents in the problem and use reinforcement learning to learn cooperatively from the environment. By making considerable theory on the seller's inventory policy, refill period, and the arrival procedure of the customers, the problem turn out to be Markov decision process model thus facilitating to apply learning algorithms. The novelty of this approach lies in the enhanced implementation of the reinforcement learning by means of Sarsa learning and Sarsa(λ) learning algorithms. The paper shows implementation results and performance comparison between multi-agent learning algorithms i.e. Strategy Sharing and Joint Reward algorithm and proposed cooperative multi-agent learning algorithms using reinforcement learning methods.