arXiv · 2611.18035
RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime
Abstract
On-device reinforcement learning runs a periodic actor and a learner on one embedded GPU shared with other workloads. Because the learner produces the actor's weights, existing designs stall the actor or let its policy drift. We present RL$^{\mathrm{RT}}$, an on-device runtime that makes this coupling a tunable parameter: a refresh bound limits actor releases between refreshes, and a GPU permit with slack-aware admission prioritises the actor and fills spare time with training atop any base scheduler. Under the real refresh cost on two Jetson boards, RL$^{\mathrm{RT}}$ keeps a 16.8 M-parameter policy's deadline misses below 1%, against 85 to 100% without it.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Zexin Li, Xinwei Gao, Arvind Easwaran. 2026-11-13. RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime. https://searcharxiv.com/abs/2611.18035
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.