# Successor Options: An Option Discovery Framework for Reinforcement Learning

## TL;DR

This paper introduces Successor Options, a framework for discovering options in reinforcement learning that navigate to landmark states using Successor Representations, scalable to high-dimensional spaces and applicable to robotic control.

## Contribution

It presents a novel method for option discovery based on landmark states and Successor Representations, including an incremental version for complex environments.

## Key findings

- Effective in grid-world environments
- Scalable to high-dimensional robotic tasks
- Improves navigation efficiency

## Abstract

The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically entailed building options, that navigate to bottleneck states. This work adopts a complementary approach, where we attempt to discover options that navigate to landmark states. These states are prototypical representatives of well-connected regions and can hence access the associated region with relative ease. In this work, we propose Successor Options, which leverages Successor Representations to build a model of the state space. The intra-option policies are learnt using a novel pseudo-reward and the model scales to high-dimensional spaces easily. Additionally, we also propose an Incremental Successor Options model that iterates between constructing Successor Representations and building options, which is useful when robust Successor Representations cannot be built solely from primitive actions. We demonstrate the efficacy of our approach on a collection of grid-worlds, and on the high-dimensional robotic control environment of Fetch.