LGAIMLNov 30, 2017

Variational Deep Q Network

arXiv:1711.11225v126 citations
Originality Incremental advance
AI Analysis

This work addresses exploration efficiency in reinforcement learning for researchers and practitioners, presenting an incremental improvement over existing DQN methods.

The paper tackles the challenge of approximating the probability distribution of value function parameters in Deep Q Networks by introducing a variational inference framework, achieving efficient exploration and strong performance on large-scale chain Markov Decision Processes.

We propose a framework that directly tackles the probability distribution of the value function parameters in Deep Q Network (DQN), with powerful variational inference subroutines to approximate the posterior of the parameters. We will establish the equivalence between our proposed surrogate objective and variational inference loss. Our new algorithm achieves efficient exploration and performs well on large scale chain Markov Decision Process (MDP).

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes