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 consider the problem of synthetically generating data that can closelyresemble human decisions made in the context of an interactive human-AI systemlike a computer game. We propose a novel algorithm that can generate synthetic,human-like, decision making data while starting from a very small set ofdecision making data collected from humans. Our proposed algorithm integratesthe concept of reward shaping with an imitation learning algorithm to generatethe synthetic data. We have validated our synthetic data generation techniqueby using the synthetically generated data as a surrogate for human interactiondata to solve three sequential decision making tasks of increasing complexitywithin a small computer game-like setup. Different empirical and statisticalanalyses of our results show that the synthetically generated data cansubstitute the human data and perform the game-playing tasks almostindistinguishably, with very low divergence, from a human performing the sametasks.

Synthetically Generating Human-like Data for Sequential Decision Making Tasks via Reward-Shaped Imitation Learning