Back to search

Georgia Institute of Technology

Integrating reinforcement learning into a programming language

Abstract

dc:description.abstract

Reinforcement learning is a promising solution to the intelligent agent problem, namely, given the state of the world, which action should an agent take to maximize goal attainment. However, reinforcement learning algorithms are slow to converge for larger state spaces and using reinforcement learning in agent programs requires detailed knowledge of reinforcement learning algorithms. One approach to solving the curse of dimensionality in reinforcement learning is decomposition. Modular reinforcement learning, as it is called in the literature, decomposes an agent into concurrently running reinforcement learning modules that each learn a ``selfish'' solution to a subset of the original problem. For example, a bunny agent might be decomposed into a module that avoids predators and a module that finds food. Current approaches to modular reinforcement learning support decomposition but, because the reward scales of the modules must be comparable, they are not composable -- a module written for one agent cannot be reused in another agent without modifying its reward function. This dissertation makes two contributions: (1) a command arbitration algorithm for modular reinforcement learning that enables composability by decoupling the reward scales of reinforcement learning modules, and (2) a Scala-embedded domain-specific language -- AFABL (A Friendly Adaptive Behavior Language) -- that integrates modular reinforcement learning in a way that allows programmers to use reinforcement learning without knowing much about reinforcement learning algorithms. We empirically demonstrate the reward comparability problem and show that our command arbitration algorithm solves it, and we present the results of a study in which programmers used AFABL and traditional programming to write a simple agent and adapt it to a new domain, demonstrating the promise of language-integrated reinforcement learning for practical agent software engineering.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2017

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Simpkins, Christopher Lee
Advisor dc:contributor.advisor
  • Isbell, Charles L.
Committee members dc:contributor.committeemember
  • Bodner, Douglas
  • Riedl, Mark
  • Rugaber, Spencer
  • Thomaz, Andrea

Subjects

dc:subject × 8

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/58683

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Simpkins, Christopher Lee. Integrating reinforcement learning into a programming language. Doctoral thesis, Georgia Institute of Technology, 2017. http://hdl.handle.net/1853/58683