Introspective Planning: Aligning Robots’ Uncertainty with Inherent Task Ambiguity
Who Plays First? Optimizing the Order of Play in Stackelberg Games with Many Robots
Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination
Emergent Coordination through Game-Induced Nonlinear Opinion Dynamics
Fast, Smooth, and Safe: Implicit CBF through Reach-Avoid DDP
Active Uncertainty Reduction for Interaction Planning
Interpretable Trajectory Prediction via Counterfactual Responsibility
ISAACS: Iterative Soft Adversarial Actor Critic for Safety
Sim-to-Lab-to-Real: Safe Reinforcement Learning with Generalization Guarantees
Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning
