arXiv subjects

Mohamad Fares El Hajj Chehade

Publications and source records attributed to Mohamad Fares El Hajj Chehade.

3 recordsLinked to original sources

arXiv2026

TRAM: Test-Time Risk Adaptation with Mixture of Agents

Deployed reinforcement learning agents often face safety requirements that are specified only after training, such as new hazard maps, revised risk thresholds, or behavioral alignment constraints. We study zero-update deployment-time adaptation, where a fixed library of risk-neutral source policies is reused under a newly specified reward-risk tradeoff. We propose TRAM (Test-Time Risk Adaptation via Mixture of Agents), a source-scored composition rule that evaluates each source policy under the target reward and an occupancy-based deployment risk, then selects actions using risk-adjusted source scores. Unlike training-time risk-sensitive methods tied to a fixed surrogate such as return variance, TRAM supports spatial barrier exposure, divergence from a reference behavior, and local volatility risks specified at test time. We explicitly characterize TRAM as a surrogate method: it does not solve the full occupancy-control problem of the stitched policy, but admits a measurable source-hull mismatch term connecting source-scored risk to realized risk. Experiments in gridworlds, MuJoCo Reacher, Safety-Gymnasium, and an LLM alignment setting show that TRAM reduces deployment risk while preserving reward, without requiring any parameter updates at test time.

cs.LG↗

arXiv2025

LEVIS: Large Exact Verifiable Input Spaces for Neural Networks

The robustness of neural networks is crucial in safety-critical applications, where identifying a reliable input space is essential for effective model selection, robustness evaluation, and the development of reliable control strategies. Most existing robustness verification methods assess the worst-case output under the assumption that the input space is known. However, precisely identifying a verifiable input space \(\mathcal{C}\), where no adversarial examples exist, is challenging due to the possible high dimensionality, discontinuity, and non-convex nature of the input space. To address this challenge, we propose a novel framework, **LEVIS**, consisting of **LEVIS-α** and **LEVIS-\b{eta}**. **LEVIS-α** identifies a single, large verifiable ball that intersects at least two boundaries of a bounded region \(\mathcal{C}\), while **LEVIS-\b{eta}** systematically captures the entirety of the verifiable space by integrating multiple verifiable balls. Our contributions include: (1) introducing a verification framework that uses mixed-integer programming (MIP) to compute nearest and directional adversarial points, (2) integrating complementarity-constrained (CC) optimization with a reduced MIP formulation for scalability, achieving up to a 6 times runtime reduction, (3) theoretically characterizing the properties of the verifiable balls obtained by **LEVIS-α**, and (4) validating the approach across applications including electrical power flow regression and image classification, with demonstrated performance gains and geometric insights into the verifiable region.

cs.LG↗

arXiv2024

Should we use model-free or model-based control? A case study of battery management systems

Reinforcement learning (RL) and model predictive control (MPC) each offer distinct advantages and limitations when applied to control problems in power and energy systems. Despite various studies on these methods, benchmarks remain lacking and the preference for RL over traditional controls is not well understood. In this work, we put forth a comparative analysis using RL- and MPC-based controllers for optimizing a battery management system (BMS). The BMS problem aims to minimize costs while adhering to operational limits. by adjusting the battery (dis)charging in response to fluctuating electricity prices over a time horizon. The MPC controller uses a learningbased forecast of future demand and price changes to formulate a multi-period linear program, that can be solved using off-the-shelf solvers. Meanwhile, the RL controller requires no timeseries modeling but instead is trained from the sample trajectories using the proximal policy optimization (PPO) algorithm. Numerical tests compare these controllers across optimality, training time, testing time, and robustness, providing a comprehensive evaluation of their efficacy. RL not only yields optimal solutions quickly but also ensures robustness to shifts in customer behavior, such as changes in demand distribution. However, as expected, training the RL agent is more time-consuming than MPC.

eess.SY↗