Reinforcement Learning With Pattern-Based Rewards

This paper introduces an approach to deriving pattern-based rewards during reinforcement learning by cooperating agents. Rough set theory introduced by Zdzislaw Pawlak in 1982 provides a ground for deriving pattern-based rewards in the context of approximation spaces. The framework provided by an approximation space makes it possible to derive pattern-based reference rewards used to compute action rewards as well as action preferences. Approximation spaces are used to derive action-based reference rewards at the swarm intelligence level. Two different forms of reinforcement comparison are considered as a part of a study of learning in real-time by a swarm. In addition, this article introduces an artificial ecosystem test-bed that makes it possible to study learning by collections of biologically-inspired bots. The contribution of this article is the introduction of an approach to rewarding swarm behavior in the context of approximation spaces.