# Fixed-Time Resilient Integral Reinforcement Learning for Input-Constrained Unknown Nonlinear Systems Under FDI Attacks and Disturbances: A Data-Driven Admissible Warm Start

arXiv: https://arxiv.org/abs/2609.14067 · HTML: https://mlsanity.com/paper/2609.14067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 3 of its 37 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 3 of 3)

- [Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control](https://mlsanity.com/paper/1611.03537/) (2016)
- [Fixed-Time Integral Reinforcement Learning for Saturated Nonlinear Multi-Agent Systems Under FDI Attacks](https://mlsanity.com/paper/2609.06163/) (2026)
- [Koopman-based Policy Iteration for Robust Optimal Control](https://mlsanity.com/paper/2204.10987/) (2022)

## Abstract (arXiv)

This paper develops a resilient learning controller for unknown nonlinear systems operating under actuator limits, false-data-injection attacks, and external disturbances. The key idea is to learn a saturated secure policy directly from finite trajectory data while guaranteeing that both the learning error and the closed-loop state converge to compact neighborhoods within a uniform fixed time independent of initial conditions. An integral formulation removes the unknown drift from the implementable learning law, while stored informative data sustain learning after online excitation fades. To mitigate the closed-loop sensitivity to arbitrary critic initialization, pre-deployment data, which may also be reused from the replay stack, are lifted through a finite-dimensional Koopman representation to construct a stabilizing initial policy, whose inverse saturated-policy map provides a data-driven critic-weight warm start. The resulting controller preserves input constraints by construction and guarantees practical fixed-time robustness under persistent attacks and disturbances. The proposed learning and initialization architecture is further verified through a two-link robot stabilization example, where the results demonstrate rapid state recovery, bounded critic learning, reliable actuator-constraint satisfaction, and improved closed-loop behavior under informed critic initialization.