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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We consider the problem of sequential recommendation, where the currentrecommendation is made based on past interactions. This recommendation taskrequires efficient processing of the sequential data and aims to providerecommendations that maximize the long-term reward. To this end, we train afarsighted recommender by using an offline RL algorithm with the policy networkin our model architecture that has been initialized from a pre-trainedtransformer model. The pre-trained model leverages the superb ability of thetransformer to process sequential information. Compared to prior works thatrely on online interaction via simulation, we focus on implementing a fullyoffline RL framework that is able to converge in a fast and stable way. Throughextensive experiments on public datasets, we show that our method is robustacross various recommendation regimes, including e-commerce and moviesuggestions. Compared to state-of-the-art supervised learning algorithms, ouralgorithm yields recommendations of higher quality, demonstrating the clearadvantage of combining RL and transformers.

Integrating Offline Reinforcement Learning with Transformers for Sequential Recommendation