Skip to content
/ Exploration-and-Implementation-of-the-MAXQ-andQlearning-algorithms-for-the-taxi-problem Public

In this paper we re-define MAXQ and the taxi environment and Implement them in R. We then apply Qlearning to the same problem. Our conclusion is that MAXQ works as good as Qlearning for this problem. Our aim is illustrate the advantages of using hierarchical reinforcement learning methods.

3 stars 1 fork Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

khaledfouda/Exploration-and-Implementation-of-the-MAXQ-andQlearning-algorithms-for-the-taxi-problem

BranchesTags

Repository files navigation

Exploration and Implementation of the MAXQ and Qlearning algorithms for the taxi problem

In this paper we re-define MAXQ and the taxi environment and Implement them in R. We then apply Qlearning to the same problem. Our conclusion is that MAXQ works as good as Qlearning for this problem. Our aim is illustrate the advantages of using hierarchical reinforcement learning methods.

The papaer can be found above as Exploration_and_Implementation_of_the_MAXQ_andQlearning_algorithms_for_the_taxi_problem.pdf or accessed through ResearchGate

Code structure can be viewed here.

About

In this paper we re-define MAXQ and the taxi environment and Implement them in R. We then apply Qlearning to the same problem. Our conclusion is that MAXQ works as good as Qlearning for this problem. Our aim is illustrate the advantages of using hierarchical reinforcement learning methods.

Topics

r reinforcement-learning qlearning hierarchical-reinforcement-learning maxq taxi-v3

Resources

Readme
Activity

Stars

3 stars

Watchers

2 watching

Forks

1 fork
Report repository

Releases

No releases published

Packages

No packages published

Languages