Takumi Tanabe

robust optimization (1) reward modeling (1) policy optimization (1) sim-to-real transfer (1) convex optimization (1) model misspecification (1) preference learning (1) direct preference optimization (1) robust reinforcement learning (1) reinforcement learning from human feedback (1) off-policy learning (1) worst-case optimization (1) reward model (1) poisoning attack (1) safety constraint (1) label flipping (1) off-policy actor-critic (1) large language model (1) worst-case robustness (1)