An effective asynchronous framework for small scale reinforcement learning problems

Shifei Ding

doi:10.1007/s10489-019-01501-9

An effective asynchronous framework for small scale reinforcement learning problems

2019-06-11

17

PRE

AI

DOI：10.1007/s10489-019-01501-9

Original

Original request for help

Save

Abstract

En 中文

Reinforcement learning is one of the research hotspots in the field of artificial intelligence in recent years. In the past few years, deep reinforcement learning has been widely used to solve various decision-making problems. However, due to the characteristics of neural networks, it is very easy to fall into local minima when facing small scale discrete space path planning problems. Traditional reinforcement learning uses continuous updating of a single agent when algorithm executes, which leads to a slow convergence speed. Although some scholars have done some improvement work to solve these problems, there are still many shortcomings to be overcome. In order to solve the above problems, we proposed a new asynchronous tabular reinforcement learning algorithms framework in this paper, and present four new variants of asynchronous reinforcement learning algorithms. We apply these algorithms on the standard reinforcement learning environments: frozen lake problem, cliff walking problem and windy gridworld problem, and the simulation results show that these methods can solve discrete space path planning problems efficiently and well balance the exploration and exploitation.

Keywords:

Reinforcement learning

Path planning

Asynchronous framework

Machine learning

Parallel framework

An effective asynchronous framework for small scale reinforcement learning problems

Abstract

AI Summary

Journal

Organization