2020/08/04 by A. H. Bell-Thomas, Bell-Thomas, A. H.
Computer Science · #Artificial Intelligence (cs.AI) #Artificial intelligence #Bayesian Modeling and Causal Inference #Bayesian inference #Bayesian network #Bayesian probability #Computer science #Context (archaeology) #Deep learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Implementation #Inference #Machine Learning (cs.LG) #Machine learning #Robustness (evolution) #Software engineering #Stability (learning theory) #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2008.01641
published in arXiv (Cornell University) (Cornell University) · 12 pages, 5 figures
arxiv created 2020/08/04 · openalex publication_date 2020/08/04 · arxiv updated 2020/08/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
This study provides both analysis and a refined, research-ready implementation of Tang and Kucukelbir's Variational Deep Q Network, a novel approach to maximising the efficiency of exploration in complex learning environments using Variational Bayesian Inference. Alongside reference implementations of both Traditional and Double Deep Q Networks, a small novel contribution is presented - the Double Variational Deep Q Network, which incorporates improvements to increase the stability and robustness of inference-based learning. Finally, an evaluation and discussion of the effectiveness of these approaches is discussed in the wider context of Bayesian Deep Learning.