Richard Davison

Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers of active agents. We propose MARS-RA, a framework that reformulates credit ass...

Reasoning capability is fundamental in enabling Large Language Models to perform complex multi-step inference. By sampling multiple reasoning paths and selecting the most frequent answer, Self Consistency (SC) remains highly effective but fails on challenging tasks where incorrect answers dominat...