One-Shot Generalization in Offline Reinforcement Learning with WSAC-N

Bachelor Thesis (2024)
Author(s)

M.D.I. Museur (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

M.R. Weltevrede – Mentor (TU Delft - Sequential Decision Making)

M.T.J. Spaan – Mentor (TU Delft - Sequential Decision Making)

E. Congeduti – Graduation committee member (TU Delft - Computer Science & Engineering-Teaching Team)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2024
Language
English
Graduation Date
27-06-2024
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Recent work has shown that offline reinforcement learning (RL) does not generalize well to new environments compared to behavioral cloning (BC). We propose WSAC-N, an ensemble model of soft actor-critics with weights to de-emphasize actions with high variance. We compare the zero-shot generalization abilities of WSAC-N with the baseline BC in a four-room maze-like environment, testing on unseen tasks. Our findings indicate that WSAC-N has worse zero-shot generalization compared to BC, aligning with previous work. Additionally, we investigate the impact of dataset characteristics on generalization, finding that dataset size has a negligible impact, while the quality of trajectories generally has a positive effect. These results are consistent with prior research.

Files

Research_Project_Final.pdf
(pdf | 1.31 Mb)
License info not available