Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning

Fan Zhou, Zhoufan Zhu, Qi Kuang, Liwen Zhang

Keywords: Non-decreasing Quantile Function, Distributional Reinforcement Learning, Distributional Prediction Error, Exploration

Abstract: Although distributional reinforcement learning (DRL) has been widely examined in the past few years, there are two open questions people are still trying to address. One is how to ensure the validity of the learned quantile function, the other is how to efficiently utilize the distribution information. This paper attempts to provide some new perspectives to encourage the future in-depth studies in these two fields. We first propose a non-decreasing quantile function network (NDQFN) to guarantee the monotonicity of the obtained quantile estimates and then design a general exploration framework called distributional prediction error (DPE) for DRL which utilizes the entire distribution of the quantile function. In this paper, we not only discuss the theoretical necessity of our method but also show the performance gain it achieves in practice by comparing with some competitors on Atari 2600 Games especially in some hard-explored games.

One-sentence Summary: This paper introduces a general framework to obtain non-decreasing quantile estimate for Distributional Reinforcement Learning and proposes an efficient exploration method for quantile value based DRL algorithms

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=0rTUkWb7ax