English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Resolving the exploration-exploitation trade-off remains a fundamentalproblem in the design and implementation of reinforcement learning (RL)algorithms. In this paper, we focus on model-free RL using the epsilon-greedyexploration policy, which despite its simplicity, remains one of the mostfrequently used forms of exploration. However, a key limitation of this policyis the specification of $\varepsilon$. In this paper, we provide a novelBayesian perspective of $\varepsilon$ as a measure of the uniformity of theQ-value function. We introduce a closed-form Bayesian model update based onBayesian model combination (BMC), based on this new perspective, which allowsus to adapt $\varepsilon$ using experiences from the environment in constanttime with monotone convergence guarantees. We demonstrate that our proposedalgorithm, $\varepsilon$-\texttt{BMC}, efficiently balances exploration andexploitation on different problems, performing comparably or outperforming thebest tuned fixed annealing schedules and an alternative data-dependent$\varepsilon$ adaptation scheme proposed in the literature.

{\epsilon}-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning