Georgios Piliouras

Researcher@Google DeepMind·英国·OpenReview

研究方向

learning in games · multi-agent learning · equilibrium · performance · optimization · online optimization · non-convex optimization · dynamical systems · control theory · Generative Adversarial Networks · Deep Learning

5.5

合作者 (20)

Antonios Varvitsiotis

Georgios Piliouras

Online Multi-Agent Control with Adversarial Disturbances

Optimism Without Regularization: Constant Regret in Zero-Sum Games

Plasticity as the Mirror of Empowerment

Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning

Re-evaluating Open-ended Evaluation of Large Language Models

Solving Zero-Sum Convex Markov Games

Deviation Ratings: A general, clone invariant rating method

Learning and Steering Game Dynamics Towards Desirable Outcomes