Representation, Modeling, and Gradient Based Optimization in Reinforcement Learning

Abstract: Reinforcement learning is now the dominant paradigm for how an agent learns to interact with the world. The approach has lead to successes ranging across numerous domains, including game playing and robotics, and it holds much promise in new domains, from self driving cars to interactive medical applications. Some of the central challenges are:

- Representational learning: does having a good representation of the environment permit efficient reinforcement learning?

- Modeling: should we explicitly build a model of our environment or, alternatively, should we directly learn how to act?

- Optimization: in practice, deployed algorithms often use local search heuristics. Can we provably understand when these approaches are effective and provide faster and more robust alternatives?

This talk will survey a number of results on these basic questions. Throughout, we will highlight the interplay of theory, algorithm design, and practice.

machine learningoptimization and controlstatistics theory

Audience: researchers in the topic

---

Online Seminar of Mathematical Foundations of Data Science

Series comments: Description: Weekly Online Seminar

---