research
∙
09/15/2023
Chain-of-Thought Reasoning is a Policy Improvement Operator
Large language models have astounded the world with fascinating new capa...
share
research
∙
07/13/2022
A Simple Adaptive Procedure Converging to Forgiving Correlated Equilibria
Simple adaptive procedures that converge to correlated equilibria are kn...
research
∙
04/11/2022
Equilibrium Finding in Normal-Form Games Via Greedy Regret Minimization
We extend the classic regret minimization framework for approximating eq...
research
∙
04/22/2020
Trading Off Diversity and Quality in Natural Language Generation
For open-ended language generation tasks such as storytelling and dialog...
research
∙
04/04/2019