Author

Jacqueline Isaacs

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement

This work introduces Iterative Action Refinement (IAR), an iterative action-construction method that constructs control actions through a sequence of learned residual corrections, yielding REFINEPPO, which matches or exceeds the performance of standard PPO while demonstrating faster convergence on several tasks.

Sachini Weerasekara, Sagar V. Kamarthi, Jacqueline Isaacs · 1 citation