Andrew Wang

unsupervised learning (1) representation learning (1) few-shot learning (1) transfer learning (1) in-context learning (1) rationale extraction (1) markov decision process (1) belief state (1) dynamic programming (1) value iteration (1) model-based reinforcement learning (1) language model (1) process supervision (1) operator splitting (1) reasoning improvement (1) analogical reasoning (1) chain of thought (1) model-based rl (1) discounted mdp (1) large language model (1)