Exponential Family Model-Based Reinforcement Learning via Score Matching

We propose a optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded and known. SMRL uses score matching, an unnormalized density estimation technique that enables efficient estimation of the model parameter by ridge regression. SMRL achieves $\tilde O(d\sqrt{H^3T})$ regret, where $H$ is the length of each episode and $T$ is the total number of interactions.