Exponential Family Model-Based Reinforcement Learning via Score Matching
Exponential Family Model-Based Reinforcement Learning via Score Matching
复制标题
DOI:
--
复制
发表时间:
2021-12
期刊:
影响因子:
--
通讯作者:
Gen Li;Junbo Li;N. Srebro;Zhaoran Wang;Zhuoran Yang
中科院分区:
文献类型:
--
作者:
Gen Li;Junbo Li;N. Srebro;Zhaoran Wang;Zhuoran Yang
We propose an 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. Under standard regularity assumptions, SMRL achieves $\tilde O(d\sqrt{H^3T})$ online regret, where $H$ is the length of each episode and $T$ is the total number of interactions (ignoring polynomial dependence on structural scale parameters).