action-value

Tag

Cards List
#action-value

Q-Steer: Action-Value Guidance for Molecular Policy Optimization

arXiv cs.LG · 2026-07-30 Cached

Introduces Q-Steer, a rollout-time action-value guidance for molecular policy optimization that uses a frozen prefix-action value scorer to improve sampling without changing the online oracle budget.

0 favorites 0 likes
← Back to home

Submit Feedback