Publication
Title
A case for feature-based successor features for transfer in reinforcement learning
Author
Abstract
Successor Features stand at the boundary between modelfree and model-based Reinforcement Learning. By predicting a sum of features instead of a sum of rewards, they enable very efficient transfer learning through the General Policy Improvement Theorem. Recent work has shifted the focus of the feature space from learnt features to a well-chosen set of base rewards. While this framework greatly improves stability, it discards the flexibility to generalize outside the base reward space. In this paper, we aim to rekindle interest in "representation-based" Successor Features for transfer learning, by clarifying the possible design choices and providing simple cases where they prevail. In a robot arm scenario, we find that they more easily transfer to unseen tasks without suffering from instabilities during training. We provide visual interpretation of the learnt features to explain this performance.
Language
English
Source (book)
34th Benelux Conference on Artificial Intelligence and the 31 Belgium Dutch Conference on Machine Learning (BNAIC/BENELEARN 2022), 7-9 November, 2022, Mechelen, Belgium
Publication
2022
Volume/pages
p. 1-16
Full text (open access)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Source file
Record
Identifier
Creation 14.12.2023
Last edited 17.06.2024
To cite this reference