Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Ron Polonsky

Ron Polonsky

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1

Frequent co-authors

Perry Dong1×
Dorsa Sadigh1×
Chelsea Fin1×

Research Timeline

2026
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

This paper studies the effectiveness of pretraining the Q-function in value-based reinforce learning and finds that naive Q-function pretraining often provides little benefit over random initialization due to a fundamental mismatch between the Q-function learned during pretraining and the Q-function that online fine-tuning converges to. The authors propose Initialization via Policy Ensemble (IPE) to improve Q-function learning in online RL.

Highlighted terms show continued research focus across papers

Papers

cs.LGEmpiricalRecentJul 29, 2026

Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

Perry Dong, Ron Polonsky, Dorsa Sadigh, Chelsea Fin

This paper studies the effectiveness of pretraining the Q-function in value-based reinforce learning and finds that naive Q-function pretraining often provides little benefit over random initializatio…

View →