Foundations of Real-World Reinforcement Learning

Опубликовано 27 мая 2021, 20:22

Reinforcement learning (RL) is an approach to sequential decision making under uncertainty which formalizes the principles for designing an autonomous learning agent. The broad goal of a reinforcement learning agent is to find an optimal policy which maximizes its long-term rewards over time. Its list of applications is growing as the technology advances and continues to be further integrated into many areas, such as education, health, advertising, autonomous systems, and gaming.

By starting from the perspective of an agent which interacts with and affects its environment, RL provides an improvement upon supervised learning in situations requiring decisions, and not just predictions. In particular, it motivates exploratory actions to discover novel rewarding behavior in the environment, a hallmark of intelligent agents.

In this webinar—led by Microsoft Researchers John Langford, Partner Research Manager with over a decade of experience in reinforcement learning-related research, and Alekh Agarwal, Principal Research Manager and leader of the Reinforcement Learning group in Redmond—learn how RL works to impact real-world problems across a variety of domains.

Together, you'll explore:

■ The definition and uses of RL, from a general paradigm to its broad range of applications
■ The various benefits of using RL as well as its current challenges
■ The specific types of RL—contextual bandits, imitation learning, and strategic exploration
■ Where these cutting-edge methods might take the future of RL.

𝗥𝗲𝘀𝗼𝘂𝗿𝗰𝗲 𝗹𝗶𝘀𝘁:

■ Reinforcement learning for the real world with Dr. John Langford and Rafah Hosn (Podcast) - microsoft.com/en-us/research/p...
■ Real World Reinforcement Learning (Project page) - microsoft.com/en-us/research/p...
■ Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning (Publication) - microsoft.com/en-us/research/p...
■ Provably efficient reinforcement learning with rich observations (Blog) - microsoft.com/en-us/research/b...
■ ICML 2017 Tutorial on Real World Interactive Learning (Tutorial) - hunch.net/~rwil
■ Machine Learning (Theory) (John Langford’s blog) - hunch.net
■ Vowpal Wabbit (open source project) - vowpalwabbit.org
■ Reinforcement Learning (Career opportunities) - microsoft.com/en-us/research/t...
■ Alekh Agarwal (researcher profile) - microsoft.com/en-us/research/p...
■ John Langford (researcher profile) - microsoft.com/en-us/research/p...

*This on-demand webinar features a previously recorded Q&A session and open captioning.

This webinar originally aired on December 5, 2019

Explore more Microsoft Research webinars: aka.ms/msrwebinars