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

We consider a Multi-Armed Bandit problem in which the rewards arenon-stationary and are dependent on past actions and potentially on pastcontexts. At the heart of our method, we employ a recurrent neural network,which models these sequences. In order to balance between exploration andexploitation, we present an energy minimization term that prevents the neuralnetwork from becoming too confident in support of a certain action. This termprovably limits the gap between the maximal and minimal probabilities assignedby the network. In a diverse set of experiments, we demonstrate that our methodis at least as effective as methods suggested to solve the sub-problem ofRotting Bandits, and can solve intuitive extensions of various benchmarkproblems. We share our implementation athttps://github.com/rotmanmi/Energy-Regularized-RNN.

Energy Regularized RNNs for Solving Non-Stationary Bandit Problems