On the influence of intelligence in (social) intelligence testing environments
This work addresses the challenge of creating effective social intelligence tests for AI researchers, but it appears incremental as it builds on existing frameworks without claiming major breakthroughs.
The paper investigates how varying agent intelligence levels in multiagent systems affects the development of social intelligence tests, analyzing reinforcement learning algorithms in cooperative and competitive contexts using the Darwin-Wallace distribution.
This paper analyses the influence of including agents of different degrees of intelligence in a multiagent system. The goal is to better understand how we can develop intelligence tests that can evaluate social intelligence. We analyse several reinforcement algorithms in several contexts of cooperation and competition. Our experimental setting is inspired by the recently developed Darwin-Wallace distribution.