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

Multi-agent reinforcement learning has received significant interest inrecent years notably due to the advancements made in deep reinforcementlearning which have allowed for the developments of new architectures andlearning algorithms. Using social dilemmas as the training ground, we present anovel learning architecture, Learning through Probing (LTP), where agentsutilize a probing mechanism to incorporate how their opponent's behaviorchanges when an agent takes an action. We use distinct training phases andadjust rewards according to the overall outcome of the experiences accountingfor changes to the opponents behavior. We introduce a parameter eta todetermine the significance of these future changes to opponent behavior. Whenapplied to the Iterated Prisoner's Dilemma (IPD), LTP agents demonstrate thatthey can learn to cooperate with each other, achieving higher averagecumulative rewards than other reinforcement learning methods while alsomaintaining good performance in playing against static agents that are presentin Axelrod tournaments. We compare this method with traditional reinforcementlearning algorithms and agent-tracking techniques to highlight key differencesand potential applications. We also draw attention to the differences betweensolving games and societal-like interactions and analyze the training ofQ-learning agents in makeshift societies. This is to emphasize how cooperationmay emerge in societies and demonstrate this using environments whereinteractions with opponents are determined through a random encounter format ofthe IPD.

Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas