Rei Sato

one-shot learning (1) robust optimization (1) reward modeling (1) policy optimization (1) sim-to-real transfer (1) model misspecification (1) gradient-based optimization (1) direct preference optimization (1) neural architecture search (1) robust reinforcement learning (1) off-policy learning (1) worst-case optimization (1) safety constraint (1) credit assignment (1) architecture optimization (1) off-policy actor-critic (1) large language model (1) sparse propagation (1) worst-case robustness (1) gradient-based approach (1)