Kianté Brantley

reinforcement learning (3) imitation learning (3) convex constraint (2) language model (2) policy optimization (2) text generation (2) constrained reinforcement learning (2) natural policy gradient (1) language modeling (1) visual reasoning (1) markov decision process (1) bellman equation (1) value iteration (1) sequence labelling (1) natural language (1) concave optimization (1) safe reinforcement learning (1) generative model (1) relative reward (1) preference-based learning (1)