Incorporating Rivalry in Reinforcement Learning for a Competitive Game
This work addresses the social impact of AI agents in competitive interactions, which is an incremental step beyond performance-focused evaluations.
The study tackled the problem of assessing reinforcement learning agents in competitive games by incorporating rivalry as a social impact factor, with results showing changes in human perception of these agents.
Recent advances in reinforcement learning with social agents have allowed us to achieve human-level performance on some interaction tasks. However, most interactive scenarios do not have as end-goal performance alone; instead, the social impact of these agents when interacting with humans is as important and, in most cases, never explored properly. This preregistration study focuses on providing a novel learning mechanism based on a rivalry social impact. Our scenario explored different reinforcement learning-based agents playing a competitive card game against human players. Based on the concept of competitive rivalry, our analysis aims to investigate if we can change the assessment of these agents from a human perspective.