Saved in:
Bibliographic Details
Main Authors: Deng, Zeyun, Ghosh, Jasorsi, Xie, Fiona, Lu, Yuzhe, Sycara, Katia, Campbell, Joseph
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.16590
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Reinforcement learning algorithms often suffer from poor sample efficiency, making them challenging to apply in multi-task or continual learning settings. Efficiency can be improved by transferring knowledge from a previously trained teacher policy to guide exploration in new but related tasks. However, if the new task sufficiently differs from the teacher's training task, the transferred guidance may be sub-optimal and bias exploration toward low-reward behaviors. We propose an energy-based transfer learning method that uses out-of-distribution detection to selectively issue guidance, enabling the teacher to intervene only in states within its training distribution. We theoretically show that energy scores reflect the teacher's state-visitation density and empirically demonstrate improved sample efficiency and performance across both single-task and multi-task settings.