View article

Recent advances in deep reinforcement learning have demonstrated its great potential for real-world problems. However, two concerns prevent reinforcement learning from being applied: Efficiency and Efficacy. This dissertation studies how to improve the efficiency and efficacy of reinforcement learning by designing deep model-based algorithms. The access to dynamics models empowers the algorithms to plan, which is key to sequential decision making. This dissertation covers four topics: online reinforcement learning, the expressivity of neural networks in deep reinforcement learning, offline reinforcement learning, and safe reinforcement learning. For online reinforcement learning, we present an algorithmic framework with theoretical guarantees by utilizing a lower bound of performance the policy learned in the learned environment can obtain in the real environment. We also empirically verify the efficiency of …