Sample-efficient reinforcement learning

Gupta, Harsh

Permalink

https://hdl.handle.net/2142/109429 Copy

Description

Title

Sample-efficient reinforcement learning

Author(s)

Gupta, Harsh

Issue Date

2020-12-02

Director of Research (if dissertation) or Advisor (if thesis)

Srikant, Rayadurgam

Doctoral Committee Chair(s)

Srikant, Rayadurgam

Committee Member(s)

• Hajek, Bruce
• Raginsky, Maxim
• He, Niao

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Date of Ingest

2021-03-05T21:38:19Z

Keyword(s)

• reinforcement learning
• sample-efficient learning
• bandits
• q-learning
• td-learning
• stochastic approximation

Abstract

Reinforcement learning has been instrumental in the recent advances made by artificial intelligence agents in various domains. Most of these advances have been abetted by the availability of huge amounts of training data. But, in several practical applications such as those arising in wireless networks, robotics, self-driving cars etc., it is expensive and sometimes completely infeasible to collect very large amounts of data. In this work, we study four different such model-free reinforcement learning problems. The first problem we consider is the structured multi-armed bandits problem, motivated by an application in wireless networks. The second problem we consider is the bandits with two-level feedback problem, motivated by an application in panoramic video streaming. The third problem we consider is the analysis of two-time scale reinforcement learning algorithms and the final problem we consider is the analysis of the Double Q-learning algorithm. In each of these problems, our general goal is to theoretically understand the mechanics of the different moving parts in the problem and on the basis of the insights obtained from the theory, design principled practical algorithms/heuristics that are sample-efficient.

Graduation Semester

2020-12

Type of Resource

Thesis

Permalink

http://hdl.handle.net/2142/109429

Copyright and License Information

Copyright 2020 Harsh Gupta

Owning Collections