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 present an approach for the quantification of the usefulness of transferin reinforcement learning via regret bounds for a multi-agent setting.Considering a number of $\aleph$ agents operating in the same Markov decisionprocess, however possibly with different reward functions, we consider theregret each agent suffers with respect to an optimal policy maximizing heraverage reward. We show that when the agents share their observations the totalregret of all agents is smaller by a factor of $\sqrt{\aleph}$ compared to thecase when each agent has to rely on the information collected by herself. Thisresult demonstrates how considering the regret in multi-agent settings canprovide theoretical bounds on the benefit of sharing observations in transferlearning.

Transfer in Reinforcement Learning via Regret Bounds for Learning Agents