Model-based Reinforcement Learning for Continuous Control with Posterior
                Sampling

                          Ying Fan 1 Yifei Ming 1

             Abstract                in RL has been one of the main challenges: the agent is
    Balancing exploration and exploitation is crucial     expected to balance between exploring unseen state-action
    in reinforcement learning (RL). In this paper, we     pairs to gain more knowledge about the environment, and
    study model-based poste ...