Parallel Recombinative Reinforcement Learning (Extended Abstract)

This paper presents a population-based technique that is suitable for function optimization in high-dimensional binary domains. The method allows an efficient parallel implementation and is based on the combination of genetic algorithms and reinforcement learning schemes. More specifically, a population of probability vectors is considered, each member corresponding to a reinforcement learning optimizer. Each probability vector represents the adaptable parameters of a team of stochastic units whose binary outputs provide a point of the function state space. At each step of the proposed technique the population members are updated according to a reinforcement learning rule and then recombined in a manner analogous to traditional genetic algorithm operation. Special care is devoted to ensuring the desirable properties of sustained exploration capability and sustained population diversity. We shall denote the proposed population-based approach as Parallel Recombinative Reinforcement Learning (PRRL).