2 papers
cs.LG2026
Mitigating Retaliatory Algorithmic Collusion in Repeated Games
Karthik Sivachandran, Rohan Paleja
Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without commun…
cs.AI2026
Differentiable Belief-based Opponent Shaping
Aarav G Sane, Karthik Sivachandran, Rohan Paleja
Human coordination often relies on the ability to influence the beliefs of others through strategic action. In multi-agent reinforcement learning, opponent shaping attempts to repl…