This is the pre-proceedings for the RLC 2026. You may expect minor changes.
Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
Will be presented at the Reinforcement Learning Conference (RLC), Montréal, Quebec, Canada, August 15–17, 2026.
Keywords: Closed-Loop Stability, Input-to-State Stability, Practical Asymptotic Stability,
Deep reinforcement learning (RL) has achieved impressive empirical success in complex control tasks, many of which are fundamentally set-stabilization problems. To safely deploy learned policies, existing methods often modify RL algorithms to enforce strict asymptotic stability. However, these algorithmic modifications alter the core RL objective, and exact zero-error convergence is practically impossible to guarantee when using neural network function approximators. This paper offers a complementary perspective: while such algorithmic modifications are valuable for training-time safety during exploration, modifying the core RL objective is often unnecessary to guarantee the stability of the deployed policy. We prove that the unmodified discounted RL objective intrinsically guarantees closed-loop practical asymptotic stability in deterministic continuous control settings. By adapting the discrete-time input-to-state stability (ISS) framework and drawing inspiration from discounted model predictive control (MPC), we model the suboptimality induced by the discount factor and the neural network approximation error as bounded disturbances. We establish that near-optimal parameterized feedback laws steer the closed-loop system into a bounded neighborhood of the target set. The size of this neighborhood vanishes in the limit as the approximation error approaches zero and, subsequently, the discount factor approaches one.
Jan de Priester and Ricardo Sanfelice. "Intrinsic Closed-Loop Practical Asymptotic Stability in Discrete-Time Reinforcement Learning." Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
BibTeX:@article{priester2026intrinsic,
title={Intrinsic Closed-Loop Practical Asymptotic Stability in Discrete-Time Reinforcement Learning},
author={Jan de Priester and Ricardo Sanfelice},
journal={Reinforcement Learning Journal},
volume={7},
pages={},
year={2026}
}