Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization

Details Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization

2012-02-29

arxiv.org/abs/1203.0203v1

Computer Science

Learning

Scientific paper

The use of Reinforcement Learning in real-world scenarios is strongly limited by issues of scale. Most RL learning algorithms are unable to deal with problems composed of hundreds or sometimes even dozens of possible actions, and therefore cannot be applied to many real-world problems. We consider the RL problem in the supervised classification framework where the optimal policy is obtained through a multiclass classifier, the set of classes being the set of actions of the problem. We introduce error-correcting output codes (ECOCs) in this setting and propose two new methods for reducing complexity when using rollouts-based approaches. The first method consists in using an ECOC-based classifier as the multiclass classifier, reducing the learning complexity from O(A2) to O(Alog(A)). We then propose a novel method that profits from the ECOC's coding dictionary to split the initial MDP into O(log(A)) seperate two-action MDPs. This second method reduces learning complexity even further, from O(A2) to O(log(A)), thus rendering problems with large action sets tractable. We finish by experimentally demonstrating the advantages of our approach on a set of benchmark problems, both in speed and performance.

Affiliated with

Also associated with

No associations

Rating

Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-526463