Parallel reinforcement learning with linear function approximation

  title={Parallel reinforcement learning with linear function approximation},
  author={Matthew Jon Grounds and D. Kudenko},
  booktitle={AAMAS '07},
  • Matthew Jon Grounds, D. Kudenko
  • Published in AAMAS '07 2007
  • Computer Science
  • In this paper, we investigate the use of parallelization in reinforcement learning (RL), with the goal of learning optimal policies for single-agent RL problems more quickly by using parallel hardware. [...] Key Method Our approach is based on agents using the SARSA(λ) algorithm, with value functions represented using linear function approximators. In our proposed method, each agent learns independently in a separate simulation of the single-agent problem.Expand Abstract
    Asynchronous Methods for Deep Reinforcement Learning
    • 3,304
    • PDF
    Massively Parallel Methods for Deep Reinforcement Learning
    • 265
    • PDF
    Concurrent Reinforcement Learning from Customer Interactions
    • 44
    • PDF
    A Learning Architecture to Support Autonomous Resource Scheduling and Allocation in the Cloud
    • 1
    • Highly Influenced


    Publications referenced by this paper.
    Reinforcement Learning: An Introduction
    • 25,519
    • Highly Influential
    • PDF
    Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
    • 1,151
    • Highly Influential
    • PDF