benchmark-tasks

Tag

Cards List
#benchmark-tasks

REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement

arXiv cs.LG ↗ · 2026-09-21 Cached

RefinePPO introduces iterative action refinement for continuous control policies, achieving performance comparable or better than standard PPO with faster convergence in benchmark tasks.

0 favorites 0 likes
← Back to home

Submit Feedback