Robust Belief-Space Games: Algorithms for Adversarial Control Under Uncertainty

Gordei VerbiiOpenReview 2025 · Submission to OWN 2025 · Rejected · OpenReview

Abstract

This paper presents a comprehensive framework for robust control in belief space under adversarial disturbances, addressing the fundamental challenge of optimal decision-making when both state uncertainty and adversarial perturbations are present. We formulate the problem as a zero-sum dynamic game in the space of probability distributions (belief space) and derive computationally tractable algorithms through finite-dimensional approximations. Our approach includes two novel CPU-efficient methods: (1) Gaussian Game-iLQG, which reduces the infinite-dimensional Hamilton-Jacobi-Bellman-Isaacs (HJBI) equation to finite-dimensional Riccati-type equations through Gaussian belief approximation, and (2) Particle Min-Max Game, which employs sample-based belief representation with alternating optimization. Extensive numerical experiments on 2D navigation and racing scenarios demonstrate that our methods achieve 15-20\% better worst-case performance compared to standard robust control approaches while maintaining computational efficiency suitable for real-time applications. The theoretical analysis provides convergence guarantees and robustness bounds, while empirical validation shows 92-95\% success rates in adversarial environments with computation times under 3 seconds on standard CPU hardware.
BibTeX
@misc{verbii2025robust,
  author = {Gordei Verbii},
  title = {{Robust Belief-Space Games: Algorithms for Adversarial Control Under Uncertainty}},
  year = {2025},
  url = {https://openreview.net/forum?id=3EMhyAwGXd},
  howpublished = {OpenReview},
  note = {Submitted to OWN 2025},
}
Figure