Ron Polonsky
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1
Frequent co-authors
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