Scientists built an AI that treats crop-raiding elephants like chess opponents to predict exactly where they’ll strike next.
arXiv · March 13, 2026 · 2603.11726
Why it matters
Wild elephants are surprisingly intelligent adversaries that learn patrol patterns and adapt their evasion tactics to find food. This algorithm uses game theory to predict elephant behavior, treating the animals as strategic competitors rather than just simple creatures of instinct.
From the abstract
We introduce an online learning algorithm for computing adaptive resource allocation policies against strategic ecological adversaries with unknown behavioral models and partial observability. Our setting addresses a fundamental limitation of security games: when adversary behavior cannot be modeled a priori, classical equilibrium-based approaches fail. We formulate the problem as regret minimization in a combinatorial action space with semi-bandit feedback, where payoffs are non-stationary and