InfoRL: Interpretable Reinforcement Learning using Information Maximization
Machine Learning
2019-05-28 v1 Artificial Intelligence
Machine Learning
Abstract
Recent advances in reinforcement learning have proved that given an environment we can learn to perform a task in that environment if we have access to some form of a reward function (dense, sparse or derived from IRL). But most of the algorithms focus on learning a single best policy to perform a given set of tasks. In this paper, we focus on an algorithm that learns to not just perform a task but different ways to perform the same task. As we know when the environment is complex enough there always exists multiple ways to perform a task. We show that using the concept of information maximization it is possible to learn latent codes for discovering multiple ways to perform any given task in an environment.
Keywords
Cite
@article{arxiv.1905.10404,
title = {InfoRL: Interpretable Reinforcement Learning using Information Maximization},
author = {Aadil Hayat and Utsav Singh and Vinay P. Namboodiri},
journal= {arXiv preprint arXiv:1905.10404},
year = {2019}
}