Deceptive Planning for Resource Allocation
Shenghui Chen, Yagiz Savas, Mustafa O. Karabag, Brian M. Sadler, Ufuk, Topcu

TL;DR
This paper introduces deception strategies for autonomous teams in adversarial environments, using maximum entropy prediction and convex optimization to mislead observers about their true objectives while achieving resource goals.
Contribution
It develops novel planning algorithms that manipulate observable behavior to deceive adversaries, combining maximum entropy prediction with divergence-based optimization.
Findings
Algorithms effectively deceive adversaries in simulated scenarios.
User study shows algorithms create ambiguity and bias towards proximate goals.
Proposed methods outperform baseline strategies in deception effectiveness.
Abstract
We consider a team of autonomous agents that navigate in an adversarial environment and aim to achieve a task by allocating their resources over a set of target locations. An adversary in the environment observes the autonomous team's behavior to infer their objective and responds against the team. In this setting, we propose strategies for controlling the density of the autonomous team so that they can deceive the adversary regarding their objective while achieving the desired final resource allocation. We first develop a prediction algorithm based on the principle of maximum entropy to express the team's behavior expected by the adversary. Then, by measuring the deceptiveness via Kullback-Leibler divergence, we devise convex optimization-based planning algorithms that deceive the adversary by either exaggerating the behavior towards a decoy allocation strategy or creating ambiguity…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Reinforcement Learning in Robotics · Distributed Control Multi-Agent Systems
