paper / csabaszepesvari / May 12 / failedLACONIC: Length-Aware Constrained Reinforcement Learning for LLM
paper / csabaszepesvari / May 12 / failedOptimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
paper / csabaszepesvari / May 12 / failedRevisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions