Shixiang Shane Gu

Reinforcement Learning (2)

reinforcement learning (3) mutual information (2) value function (2) multi-task learning (1) direct preference optimization (1) few-shot learning (1) temporal difference learning (1) variational inference (1) curriculum learning (1) preference learning (1) offline reinforcement learning (1) language model alignment (1) reinforcement learning from human feedback (1) model alignment (1) sample efficiency (1) representation learning (1) value iteration (1) state representation (1) off-policy learning (1) deep reinforcement learning (1)