FeUdal Networks for Hierarchical Reinforcement Learning

TL;DR

FeUdal Networks (FuNs) introduce a hierarchical reinforcement learning architecture with a Manager and Worker, enabling long-term credit assignment and sub-policy emergence, leading to superior performance on complex tasks.

Contribution

The paper presents a novel hierarchical RL architecture inspired by feudal reinforcement learning, with decoupled modules for different temporal resolutions, improving long-term learning.

Findings

Outperforms baseline agents on long-term credit tasks

Facilitates emergence of sub-policies for different goals

Effective on Atari and DeepMind Lab environments

Abstract

We introduce FeUdal Networks (FuNs): a novel architecture for hierarchical reinforcement learning. Our approach is inspired by the feudal reinforcement learning proposal of Dayan and Hinton, and gains power and efficacy by decoupling end-to-end learning across multiple levels -- allowing it to utilise different resolutions of time. Our framework employs a Manager module and a Worker module. The Manager operates at a lower temporal resolution and sets abstract goals which are conveyed to and enacted by the Worker. The Worker generates primitive actions at every tick of the environment. The decoupled structure of FuN conveys several benefits -- in addition to facilitating very long timescale credit assignment it also encourages the emergence of sub-policies associated with different goals set by the Manager. These properties allow FuN to dramatically outperform a strong baseline agent on tasks that involve long-term credit assignment or memorisation. We demonstrate the performance of our proposed system on a range of tasks from the ATARI suite and also from a 3D DeepMind Lab environment.