Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning
This work addresses validity and efficiency issues in DRL, which is incremental as it builds on existing methods to improve specific bottlenecks.
The paper tackles two open problems in distributional reinforcement learning by proposing a non-decreasing quantile function network to ensure valid quantile estimates and a distributional prediction error framework for efficient exploration, showing performance gains on Atari 2600 Games, especially in hard-explored games.
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.