Hanlin Zhu

reward estimation (2) task-oriented dialog (2) multi-domain dialog (2) offline reinforcement learning (2) dialog policy (2) adversarial inverse reinforcement learning (2) sample complexity (1) in-context learning (1) policy optimization (1) empirical risk minimization (1) importance sampling (1) gradient descent (1) value function approximation (1) query complexity (1) inverse reinforcement learning (1) logical reasoning (1) bilinear model (1) regret bound (1) autoregressive model (1) policy learning (1)