InfoRL: Interpretable Reinforcement Learning using Information Maximization

TL;DR

This paper introduces InfoRL, an approach that uses information maximization to learn multiple diverse policies for the same task in reinforcement learning environments, enhancing interpretability and flexibility.

Contribution

It presents a novel algorithm that learns latent codes to discover multiple ways of performing a task, extending beyond single-policy solutions.

Findings

Learns diverse policies for the same task using information maximization.

Enables interpretability by associating latent codes with different strategies.

Demonstrates effectiveness in complex environments.

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.