2021/05/15 by Xuhui Liu, Liu, Xu-Hui, Zhenghai Xue +9
Computer Science · Decision Sciences · Neuroscience · Psychology · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Machine Learning (cs.LG) #Mental Health Research Topics #Neural dynamics and brain function #Reinforcement Learning in Robotics
paper · pdf · doi:10.48550/arxiv.2105.07253
openalex publication_date 2021/05/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, recentness and corrective feedback, which are mostly heuristically designed. In this work, we start from the regret minimization objective, and obtain an optimal prioritization strategy for Bellman update that can directly maximize the return of the policy. The theory suggests that data with higher hindsight TD error, better on-policiness and more accurate Q value should be assigned with higher weights during sampling. Thus most previous criteria only consider this strategy partially. We not only provide theoretical justifications for previous criteria, but also propose two new methods to compute the prioritization weight, namely ReMERN and ReMERT. ReMERN learns an error network, while ReMERT exploits the temporal ordering of states. Both methods outperform previous prioritized sampling algorithms in challenging RL benchmarks, including MuJoCo, Atari and Meta-World.