English

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}
}
R2 v1 2026-06-23T09:23:04.162Z