Parallel reinforcement learning with linear function approximation

Matthew Grounds; Daniel Kudenko

Parallel reinforcement learning with linear function approximation

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

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. Our approach is based on agents using the SARSA(¿) 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. The agents periodically exchange information extracted from the weights of their approximators, accelerating convergence towards the optimal policy. We present empirical results for an implementation on a Beowulf cluster.

Original language	Undefined/Unknown
Pages	45
Publication status	Published - 2007

Access to Document

http://doi.acm.org/10.1145/1329125.1329179

Cite this

@conference{bf44eebe633649dd884bd6aabc94556c,

title = "Parallel reinforcement learning with linear function approximation",

abstract = "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. Our approach is based on agents using the SARSA(¿) 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. The agents periodically exchange information extracted from the weights of their approximators, accelerating convergence towards the optimal policy. We present empirical results for an implementation on a Beowulf cluster.",

author = "Matthew Grounds and Daniel Kudenko",

year = "2007",

language = "Undefined/Unknown",

pages = "45",

}

TY - CONF

T1 - Parallel reinforcement learning with linear function approximation

AU - Grounds, Matthew

AU - Kudenko, Daniel

PY - 2007

Y1 - 2007

N2 - 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. Our approach is based on agents using the SARSA(¿) 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. The agents periodically exchange information extracted from the weights of their approximators, accelerating convergence towards the optimal policy. We present empirical results for an implementation on a Beowulf cluster.

AB - 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. Our approach is based on agents using the SARSA(¿) 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. The agents periodically exchange information extracted from the weights of their approximators, accelerating convergence towards the optimal policy. We present empirical results for an implementation on a Beowulf cluster.

M3 - Paper

SP - 45

ER -