Bayesian regularization of empirical MDPs

arxiv(2022)

引用 0|浏览41
暂无评分
摘要
In most applications of model-based Markov decision processes, the parameters for the unknown underlying model are often estimated from the empirical data. Due to noise, the policy learnedfrom the estimated model is often far from the optimal policy of the underlying model. When applied to the environment of the underlying model, the learned policy results in suboptimal performance, thus calling for solutions with better generalization performance. In this work we take a Bayesian perspective and regularize the objective function of the Markov decision process with prior information in order to obtain more robust policies. Two approaches are proposed, one based on $L^1$ regularization and the other on relative entropic regularization. We evaluate our proposed algorithms on synthetic simulations and on real-world search logs of a large scale online shopping store. Our results demonstrate the robustness of regularized MDP policies against the noise present in the models.
更多
查看译文
关键词
bayesian regularization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要