The National Science Foundation Workshop on Reinforcement Learning

نویسندگان

  • Sridhar Mahadevan
  • Leslie Pack Kaelbling
چکیده

learning, neural networks, robotics, AI, and engineering. In recognition of the growing importance of reinforcement learning, it seemed an opportune time to bring together leading researchers from these areas for a three-day meeting consisting of general and wide-ranging discussions. The National Science Foundation (NSF) sponsored the workshop with a generous grant to cover the travel and lodging costs of all participants. The participants sought to assess the state of the art of reinforcement learning today; outline promising directions for further work; clarify links between reinforcement learning and existing work in dynamic programming; and, finally, explore potential industrial applications of reinforcement learning.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The NSF Workshop on Reinforcement Learning : Summary and Observations 1

Reinforcement learning (RL) has become one of the most actively studied learning frameworks in the area of intelligent autonomous agents. This article describes the results of a three-day meeting of leading researchers in this area, sponsored by the National Science Foundation (NSF). As RL is an interdisciplinary topic, the workshop brought together researchers from a variety of elds, including...

متن کامل

Report of the 1996 Workshop on Reinforcement Learning Sponsored by the National Science Foundation Preface and Acknowledgements

This document describes the results of a two-day meeting of leading researchers in the area of reinforcement learning (RL). As RL is an interdisciplinary topic, the aim was to bring together researchers from a variety of elds, including machine learning, neural networks, arti cial intelligence, robotics, and operations research. Thirty leading researchers in the eld participated in the workshop...

متن کامل

A Distributed Reinforcement Learning Scheme for Network Routing

In this paper we describe a self-adjusting algorithm for packet routing, in which a reinforcement learning module is embedded into each node of a switching network. Only local communication is used to keep accurate statistics at each node on which routing policies lead to minimal delivery times. In simple experiments involving a 36-node, irregularly connected network, this learning approach pro...

متن کامل

An Electronic Market-Maker

This paper presents an adaptive learning model for market-making under the reinforcement learning framework. Reinforcement learning is a learning technique in which agents aim to maximize the long-term accumulated rewards. No knowledge of the market environment, such as the order arrival or price process, is assumed. Instead, the agent learns from realtime market experience and develops explici...

متن کامل

Importance Sampling for Reinforcement Learning with Multiple

This thesis considers three complications that arise from applying reinforcement learning to a real-world application. In the process of using reinforcement learning to build an adaptive electronic market-maker, we find the sparsity of data, the partial observability of the domain, and the multiple objectives of the agent to cause serious problems for existing reinforcement learning algorithms....

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • AI Magazine

دوره 17  شماره 

صفحات  -

تاریخ انتشار 1996