arXiv Machine Learning By Pu Li, Tao Tan, Hong Xie, Xiaoyu Shi, Mingsheng Shang

Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection

Read the original on arXiv Machine Learning →

arXiv:2608. 12912v1 Announce Type: new Abstract: This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.