Project description
Reinforcement learning takes a great leap forward
Learning from interaction is a fundamental idea underlying nearly all theories of learning and intelligence. Compared with other approaches to machine learning, reinforcement learning is much more focussed on computational issues that arise when software agents learn from interactions with an environment. The EU-funded COLT-MDP project aims to advance state-of-the-art theoretical approaches to reinforcement learning. The study will revolve around three pillars. The design of compact representation models will enable researchers to better structure complex problems. This could extend the applicability of reinforcement learning to many fields. Furthermore, researchers will develop efficient computation algorithms. Driven by public concerns, a growing body of research will address questions related to fairness and privacy in artificial intelligence.
Objective
Computational learning theory has been highly successful over the last three decades, both in providing deep mathematical theories and in influencing the practice of machine learning. One of the great recent successes of computational learning theory has been the study of online learning and multi-arm bandits. This line of research has been highly successful, both theoretically and practically, addressing many important applications. Unfortunately, the recent theoretical progress in Markov Decision Process and reinforcement learning has been slower.
Based on my fundamental contributions to reinforcement learning (e.g. policy gradient, sparse sampling and trajectory trees), to online learning and machine learning in general, I propose to take the theoretical and practical success of online learning to the “next level” by making significant breakthroughs in reinforcement learning. Our main aim is to advance the state of the art in the theory of reinforcement learning, and our research will revolve around three pillars: (1) compact representation, (2) efficient computation and (3) societal challenges, including fairness and privacy.
A successful project will greatly impact reinforcement learning in all its stages. Modelling: Introducing new compact representation models, will enhance our understanding how to structure complex problems, which would greatly extend the applicability of reinforcement learning. Efficient computation: New algorithmic methodologies will give new insight for overcoming computational and statistical barriers both for planning and learning. Learning: New learning paradigms would address fundamental issues of copping with uncertainties in complex control environments of reinforcement learning. Societal challenges: Allowing the community to understand, assess, address and overcome societal challenges is of the greatest importance to the acceptance of AI methodologies by the general public.
Fields of science
Programme(s)
Topic(s)
Funding Scheme
ERC-ADG - Advanced GrantHost institution
69978 Tel Aviv
Israel