Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
Read the original on arXiv AI →The paper introduces AnchorQ, a method that improves sample-efficient reinforcement learning for policy refinement by using flow-reversed action anchors. AnchorQ maps reference behaviors to state-conditioned latent anchors, samples local particles around these anchors, and employs value-guided sampling to explore promising refinements. Experiments on simulated and real-world manipulation tasks show that AnchorQ outperforms state-of-the-art post-training baselines, achieving a 37% higher real-world success rate and 97% greater simulated task throughput within the same interaction budget.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.