Boyi Liu

model-based reinforcement learning (3) neural network (2) policy gradient (2) graph matching (2) function approximation (1) reinforcement learning from human feedback (1) game theory (1) generalization bound (1) graph representation learning (1) global convergence (1) primal-dual optimization (1) language model alignment (1) constrained reinforcement learning (1) relational reasoning (1) markov decision process (1) direct preference optimization (1) mirror descent (1) bilevel optimization (1) fenchel duality (1) reinforcement learning (1)