Preux, Philippe

Adversarially Guided Actor-Critic

2021 · arXiv (Cornell University)

Despite definite success in deep reinforcement learning problems,\nactor-critic algorithms are still confronted with sample inefficiency in\ncomplex environments, particularly in tasks where efficient exploration is a\nbottleneck. These methods consider a policy (the actor) and a value …

Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop

2024 · arXiv (Cornell University)

Embracing the pursuit of intrinsically explainable reinforcement learning raises crucial questions: what distinguishes explainability from interpretability? Should explainable and interpretable agents be developed outside of domains where transparency is imperative? What advantages do interpretable policies …