Ruomeng Ding

large language model (2) decision making (1) sequential decision making (1) preference learning (1) in-context learning (1) prompt engineering (1) out-of-distribution generalization (1) reinforcement learning from human feedback (1) distribution shift (1) monte carlo tree search (1) reward model (1) skill learning (1) credit assignment (1) hidden state regularization (1) reward over-optimization (1) cognitive mapping (1) thought prompting (1) game of 24 (1) thought generation (1) reinforcement learning (1)