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/

Zendy Plus

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

Zendy Tools

Zendy Open

When interacting with other decision-making agents in non-adversarialscenarios, it is critical for an autonomous agent to have inferable behavior:The agent's actions must convey their intention and strategy. We model theinferability problem using Stackelberg games with observations where a leaderand a follower repeatedly interact. During the interactions, the leader uses afixed mixed strategy. The follower does not know the leader's strategy anddynamically reacts to the statistically inferred strategy based on the leader'sprevious actions. In the inference setting, the leader may have a lowerperformance compared to the setting where the follower has full information onthe leader's strategy. We refer to the performance gap between these settingsas the inferability gap. For a variety of game settings, we show that theinferability gap is upper-bounded by a function of the number of interactionsand the stochasticity level of the leader's strategy, encouraging the use ofinferable strategies with lower stochasticity levels. We also analyze bimatrixStackelberg games and identify a set of games where the leader's near-optimalstrategy may suffer from a large inferability gap.

When Should a Leader Act Suboptimally? The Role of Inferability in Repeated Stackelberg Games