Luise Ge

game theory (1) reinforcement learning from human feedback (1) reward function (1) lifted inference (1) first-order logic (1) reward learning (1) bradley-terry-luce model (1) social choice (1) polynomial time (1) human feedback (1) preference aggregation (1) reasoning model (1) reward function learning (1) ai alignment (1) social choice theory (1) voting rule (1) relational probabilistic inference (1) sum-of-squares logic (1) conversational model (1) axiomatic analysis (1)