Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula

no code implementations • 3 Nov 2023 • Aryaman Reddi, Maximilian Tölle, Jan Peters, Georgia Chalvatzaki, Carlo D'Eramo

To this end, Robust Adversarial Reinforcement Learning (RARL) trains a protagonist against destabilizing forces exercised by an adversary in a competitive zero-sum Markov game, whose optimal solution, i. e., rational strategy, corresponds to a Nash equilibrium.

reinforcement-learning Reinforcement Learning (RL)