Q-Managed: A new algorithm for a multiobjective reinforcement learning

Multi-objective reinforcement learning involves the use of techniques to address problems with multiple objectives. To resolve this, we a hybrid multi-objective optimization method that provides mathematical guarantee all policies belonging Pareto Front can be found. The hybridization gave rise Q-Managed, which is given by ε−constraint and Q-Learning algorithm, where first limits environment dynamically based on agent’s learning. Thus, when region no longer improvement, it becomes constraint, preventing agent from returning. simplicity its performance come single-policy algorithms.