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

In 2021 the Johns Hopkins University Applied Physics Laboratory held aninternal challenge to develop artificially intelligent (AI) agents that couldexcel at the collaborative card game Hanabi. Agents were evaluated on theirability to play with human players whom the agents had never previouslyencountered. This study details the development of the agent that won thechallenge by achieving a human-play average score of 16.5, outperforming thecurrent state-of-the-art for human-bot Hanabi scores. The winning agent'sdevelopment consisted of observing and accurately modeling the author'sdecision making in Hanabi, then training with a behavioral clone of the author.Notably, the agent discovered a human-complementary play style by firstmimicking human decision making, then exploring variations to the human-likestrategy that led to higher simulated human-bot scores. This work examines indetail the design and implementation of this human compatible Hanabi teammate,as well as the existence and implications of human-complementary strategies andhow they may be explored for more successful applications of AI in humanmachine teams.

Reinforcement Learning on Human Decision Models for Uniquely Collaborative AI Teammates