Shenao Zhang

model-based reinforcement learning (3) regret bound (2) policy optimization (2) policy gradient (2) language model alignment (1) posterior sampling (1) reinforcement learning from human feedback (1) robot learning (1) value function (1) reparameterization gradient (1) sublinear regret (1) model-free reinforcement learning (1) credit assignment (1) gradient variance (1) global optimality (1) adversarial regularizer (1) exploration efficiency (1) conservative policy optimization (1) multi-step reasoning (1) contact dynamics (1)