January 2026

We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $ell$ steps of future transition and reward realizations: the exact state the agent would reach and the rewards it would collect under any possible course of action. While it has been shown that such information can drastically boost the value, finding the optimal policy is NP-hard, and it is common to apply one of two tractable heuristics: processing the lookahead in […]

Ver mais

Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to backdoor attacks. Existing attack strategies typically struggle against safety-constrained algorithms (e.g., CQL) due to inefficient random poisoning and the use of easily detectable Out-of-Distribution (OOD) triggers. In this paper, we propose CS-GBA (Critical Sample-based Gradient-guided Backdoor Attack), a novel framework designed to achieve high stealthiness and destructiveness under a strict budget. Leveraging the theoretical insight that samples with high Temporal Difference (TD) errors […]

Ver mais

The World Wide Web thrives on intelligent services that rely on accurate time series classification, which has recently witnessed significant progress driven by advances in deep learning. However, existing studies face challenges in domain incremental learning. In this paper, we propose a lightweight and robust dual-causal disentanglement framework (DualCD) to enhance the robustness of models under domain incremental scenarios, which can be seamlessly integrated into time series classification models. Specifically, DualCD first introduces a temporal feature disentanglement module […]

Ver mais

Over the past few years working with data teams inside large enterprises, I’ve met a lot of data leaders who tell me they’ve tried and failed to “do DataOps.” The pattern is usually the same. They write standards, add a few tests, and stand up observability tools. Processes get documented. Release checklists are made. Teams try—earnestly—to follow them. And then the backlog piles up, exceptions multiply, and the team has to hold it all together with memory and […]

Ver mais

Author(s): Ayoub Nainia Originally published on Towards AI. Being a PhD student working on AI and NLP, I’ve spent quite some time using PyTorch and other high-level frameworks that abstract away the GPU. But recent discussions about whether I should learn CUDA pushed me to step back and revisit the basics: where all of this started, and why it changed. This isn’t an official “learning guide” or a course roadmap. It’s going back to first principles and sharing […]

Ver mais