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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present Bayesian Team Imitation Learner (BTIL), an imitation learningalgorithm to model the behavior of teams performing sequential tasks inMarkovian domains. In contrast to existing multi-agent imitation learningtechniques, BTIL explicitly models and infers the time-varying mental states ofteam members, thereby enabling learning of decentralized team policies fromdemonstrations of suboptimal teamwork. Further, to allow for sample- andlabel-efficient policy learning from small datasets, BTIL employs a Bayesianperspective and is capable of learning from semi-supervised demonstrations. Wedemonstrate and benchmark the performance of BTIL on synthetic multi-agenttasks as well as a novel dataset of human-agent teamwork. Our experiments showthat BTIL can successfully learn team policies from demonstrations despite theinfluence of team members' (time-varying and potentially misaligned) mentalstates on their behavior.

Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations