Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation
Ethan Hirschowitz, Fabio Ramos
Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amounts to shifting the base pol…
cs.LG2025
Informing Acquisition Functions via Foundation Models for Molecular Discovery
Qi Chen, Fabio Ramos, Alán Aspuru-Guzik +1
Bayesian Optimization (BO) is a key methodology for accelerating molecular discovery by estimating the mapping from molecules to their properties while seeking the optimal candidat…
cs.LG2025
Harnessing Bounded-Support Evolution Strategies for Policy Refinement
Ethan Hirschowitz, Fabio Ramos
Improving competent robot policies with on-policy RL is often hampered by noisy, low-signal gradients. We revisit Evolution Strategies (ES) as a policy-gradient proxy and localize…