Reinforcement Learning Strategy for A-Team Solving the Resource-Constrained Project Scheduling Problem

In this paper the strategy for the A-Team with Reinforcement Learning (RL) for solving the Resource Constrained Project Scheduling Problem (RCPSP) is proposed and experimentally validated. The RCPSP belongs to the NP-hard problem class. To solve this problem a team of asynchronous agents (A-Team) has been implemented using JABAT multiagent system. An A-Team is the set of objects including multiple agents and the common memory which through interactions produce solutions of optimization problems. These interactions are usually managed by the static strategy. In this paper the dynamic learning strategy is suggested. The proposed strategy based on reinforcement learning supervises interactions between optimization agents and the common memory. To validate the approach computational experiment has been carried out.