Exploring Variational Deep Q Networks
This work addresses exploration challenges in reinforcement learning for AI agents, presenting incremental improvements to existing methods.
The study analyzed and implemented Variational Deep Q Networks to improve exploration efficiency in complex learning environments, introducing a Double Variational Deep Q Network that enhanced stability and robustness.
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.