dynamics shift 1flow-based transformations 1policy adaptation 1residual reinforcement learning 1sim-to-real transfer 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation
Ethan Hirschowitz, Fabio Ramos
The paper introduces Warp RL, a method that adapts a pretrained robot policy by applying an invertible, state‑conditioned transformation to its action distribution, enabling shape…
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…