Back to search

Cornell University

Towards Safe, Efficient, and Steerable Reinforcement Learning

Abstract

dc:description.abstract

Reinforcement Learning (RL), the maximization of expected cumulative reward, is a framework for interactive decision-making that has produced many successes in games, recommendation systems, drug discovery, and large language models (LLMs). Despite these successes, existing algorithms can be brittle and inefficient, making RL difficult and costly to use, especially in safety-critical settings. My broad goal is to make RL agents much more efficient, robust, and practical, and in this thesis, we make progress towards this goal via the following three directions: 1. Safety and Robustness: How can we train agents to avoid unsafe behaviors while being robust to unseen or even adversarial situations? 2. Efficiency and Adaptivity: How can we design algorithms that use available data to the fullest and that can adaptively learn faster in realistic (non-adversarial) environments? 3. Steerable and Transferable RL: How can we use vast knowledge from related tasks to reduce the cost of exploration and representation learning, and to learn a steerable multi-task agent? Each aim is developed in a dedicated chapter, beginning with foundational theory and algorithms, and culminating in real-world applications that demonstrate practical impact. Together, they chart a path toward RL that is safer, more efficient, and more broadly usable.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wang, Kaiwen
Chair dc:contributor.chair
  • Kallus, Nathan
Committee members dc:contributor.committeemember
  • Sun, Wen
  • Tardos, Eva

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
17423437
Dc Identifier Other
ProQuest Submission ID: 15299
ProQuest Publication ID: 32245744

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Wang, Kaiwen. Towards Safe, Efficient, and Steerable Reinforcement Learning. Doctor of Philosophy thesis, Cornell University, 2025. https://hdl.handle.net/1813/121079