In dynamic Stackelberg games with mid-game belief updates, assuming an incorrect follower best-response model can yield strictly lower leader cost than knowing the true model.
Active Inverse Learning in Stackelberg Trajectory Games
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Presents an SHT-driven framework for adversarial decision-making in partially observable multi-agent systems formulated as a partially observable Stackelberg game, with semi-explicit optimal controls for the blue team in LQ settings and iterative/ML methods for the red team.
The paper provides stability criteria for multi-agent systems with heterogeneous model predictive game controllers and quantifies sensitivity of equilibria to objective misspecifications.
citing papers explorer
-
When the Correct Model Fails: The Optimality of Stackelberg Equilibria with Follower Intention Updates
In dynamic Stackelberg games with mid-game belief updates, assuming an incorrect follower best-response model can yield strictly lower leader cost than knowing the true model.
-
Adversarial Decision-Making in Partially Observable Multi-Agent Systems: A Sequential Hypothesis Testing Approach
Presents an SHT-driven framework for adversarial decision-making in partially observable multi-agent systems formulated as a partially observable Stackelberg game, with semi-explicit optimal controls for the blue team in LQ settings and iterative/ML methods for the red team.
-
Stability and Sensitivity Analysis for Objective Misspecifications Among Model Predictive Game Controllers
The paper provides stability criteria for multi-agent systems with heterogeneous model predictive game controllers and quantifies sensitivity of equilibria to objective misspecifications.