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

Inverse reinforcement learning (IRL) aims to explain observed strategicbehavior by fitting reinforcement learning models to behavioral data. However,traditional IRL methods are only applicable when the observations are in theform of state-action paths. This assumption may not hold in many real-worldmodeling settings, where only partial or summarized observations are available.In general, we may assume that there is a summarizing function $\sigma$, whichacts as a filter between us and the true state-action paths that constitute thedemonstration. Some initial approaches to extending IRL to such situations havebeen presented, but with very specific assumptions about the structure of$\sigma$, such as that only certain state observations are missing. This paperinstead focuses on the most general case of the problem, where no assumptionsare made about the summarizing function, except that it can be evaluated. Wedemonstrate that inference is still possible. The paper presents exact andapproximate inference algorithms that allow full posterior inference, which isparticularly important for assessing parameter uncertainty in this challenginginference situation. Empirical scalability is demonstrated to reasonably sizedproblems, and practical applicability is demonstrated by estimating theposterior for a cognitive science RL model based on an observed user's taskcompletion time only.

Inverse Reinforcement Learning from Summary Data