Eigenoption Discovery through the Deep Successor Representation

TL;DR

This paper introduces a deep reinforcement learning method for autonomous discovery of eigenoptions using successor representations, enabling hierarchical task decomposition directly from raw pixel inputs in complex environments.

Contribution

It extends eigenoption discovery algorithms to stochastic and raw pixel settings, leveraging deep successor representations for effective option learning.

Findings

Successfully discovers eigenoptions in Atari games

Handles stochastic transitions without handcrafted features

Learns non-linear state representations from pixels

Abstract

Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning. However, autonomously learning effective sets of options is still a major challenge in the field. In this paper we focus on the recently introduced idea of using representation learning methods to guide the option discovery process. Specifically, we look at eigenoptions, options obtained from representations that encode diffusive information flow in the environment. We extend the existing algorithms for eigenoption discovery to settings with stochastic transitions and in which handcrafted features are not available. We propose an algorithm that discovers eigenoptions while learning non-linear state representations from raw pixels. It exploits recent successes in the deep reinforcement learning literature and the equivalence between proto-value functions and the successor representation. We use traditional tabular domains to provide intuition about our approach and Atari 2600 games to demonstrate its potential.