Xinwen Hou

Self-Attention for Deep Reinforcement Learning

2019

Reinforcement learning is concerned with how software agents ought to take actions according to the state of the environment so as to maximize some notion of cumulative reward. Therefore, in-depth study and mining of the …

The $f$-Divergence Reinforcement Learning Framework

2021 · arXiv (Cornell University)

The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \emph{$f$-Divergence Reinforcement Learning (FRL)}. In FRL, the policy evaluation …