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

It is challenging for reinforcement learning (RL) algorithms to succeed inreal-world applications like financial trading and logistic system due to thenoisy observation and environment shifting between training and evaluation.Thus, it requires both high sample efficiency and generalization for resolvingreal-world tasks. However, directly applying typical RL algorithms can lead topoor performance in such scenarios. Considering the great performance ofensemble methods on both accuracy and generalization in supervised learning(SL), we design a robust and applicable method named Ensemble Proximal PolicyOptimization (EPPO), which learns ensemble policies in an end-to-end manner.Notably, EPPO combines each policy and the policy ensemble organically andoptimizes both simultaneously. In addition, EPPO adopts a diversity enhancementregularization over the policy space which helps to generalize to unseen statesand promotes exploration. We theoretically prove EPPO increases explorationefficacy, and through comprehensive experimental evaluations on various tasks,we demonstrate that EPPO achieves higher efficiency and is robust forreal-world applications compared with vanilla policy optimization algorithmsand other ensemble methods. Code and supplemental materials are available athttps://seqml.github.io/eppo.

Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble