Position: Deployed Reinforcement Learning should be Continual

June 01, 2026 ยท Grace Period ยท ๐Ÿ› the ICML 2026 Position Paper Track

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Parnian Behdin, Kevin Roice, Golnaz Mesbahi arXiv ID 2606.04029 Category cs.LG: Machine Learning Cross-listed cs.AI Citations 0 Venue the ICML 2026 Position Paper Track
Abstract
Reinforcement Learning (RL) has received increasing attention and adoption in real-world use cases. Most of these systems follow a train-then-fix paradigm, where trained agents do not learn while interacting with the world until performance degrades and retraining becomes necessary. In this position paper, we argue that deploying an agent that is incapable of optimality, but receives an evaluative reward signal, is inherently a continual RL problem. We identify four sources of non-stationarity after deployment that necessitate never-ending learning, and highlight why the best deployed agents never stop adapting. We analyze successful examples of continual RL in the real world, and present the community with the advantages and measures to move away from the current train-then-fix paradigm.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning