Towards autonomous behavior learning of non-player characters in games

作者：

Highlights：

• One computational model unifying imitative learning and reinforcement learning.

• Two integration strategies: Dual-Stage Learning (DSL) and Mixed Model Learning (MML).

• Benchmark based on creating intelligent Non-Player Characters (NPC) in games.

• Both DSL and MML produce NPCs with faster learning and better performance.

摘要

•One computational model unifying imitative learning and reinforcement learning.•Two integration strategies: Dual-Stage Learning (DSL) and Mixed Model Learning (MML).•Benchmark based on creating intelligent Non-Player Characters (NPC) in games.•Both DSL and MML produce NPCs with faster learning and better performance.

论文关键词：Behavior learning,Reinforcement learning,Imitative learning,Self-organizing neural network,Intelligent agent

论文评审过程：Received 27 January 2014, Revised 6 February 2016, Accepted 23 February 2016, Available online 4 March 2016, Version of Record 22 March 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.02.043