SOURCE-LINKED INTELLIGENCE

Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency

arXiv · AI, language, vision and robotics · article · Aug 24, 2026 · UTC

While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist policies, such as VLAs, poses a fundamental obstacle to effective RL improvement. In particular, their severe inference latency---which can lead to pauses or jerky movements---can alter the effective environment dynamics and, if not correctly accounted for, break the Markov assumption that RL relies on, causing standard RL algorithms to fail completely. In this work, we introduce a latency-aware framework, Asynchronous RL with Intermediate Infor

Read original source ↗ Open in workspace

recordType

paper

region

Global