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

Learning to play optimally against any mixture over a diverse set ofstrategies is of important practical interests in competitive games. In thispaper, we propose simplex-NeuPL that satisfies two desiderata simultaneously:i) learning a population of strategically diverse basis policies, representedby a single conditional network; ii) using the same network, learnbest-responses to any mixture over the simplex of basis policies. We show thatthe resulting conditional policies incorporate prior information about theiropponents effectively, enabling near optimal returns against arbitrary mixturepolicies in a game with tractable best-responses. We verify that such policiesbehave Bayes-optimally under uncertainty and offer insights in using thisflexibility at test time. Finally, we offer evidence that learningbest-responses to any mixture policies is an effective auxiliary task forstrategic exploration, which, by itself, can lead to more performantpopulations.

Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games