Genetic state-grouping algorithm for deep reinforcement learning

作者：

Highlights：

• Genetic-State Grouping Algorithm guarantees enhancing the performance of RL agents.

• The genetic algorithm has successfully been combined with Monte Carlo Tree Search.

• Video game provides a valid proving ground for testing AI’s capability.

摘要

•Genetic-State Grouping Algorithm guarantees enhancing the performance of RL agents.•The genetic algorithm has successfully been combined with Monte Carlo Tree Search.•Video game provides a valid proving ground for testing AI’s capability.

论文关键词：Reinforcement learning,Genetic algorithm,Hybrid method,Monte Carlo Tree Search,Game AI

论文评审过程：Received 27 November 2019, Revised 25 May 2020, Accepted 24 June 2020, Available online 7 July 2020, Version of Record 14 July 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113695