RLLBC-Lib is an educational code library designed to lower the entry barrier for students learning reinforcement learning (RL) in the context of learning-based control. It offers a comprehensive collection of tabular RL methods to reinforce theoretical foundations, followed by a deep RL library that mirrors the same design principles to highlight parallels between simple and state‑of‑the‑art approaches. The library also includes implementations that illustrate core RL principles, contrast RL with other learning‑based control methods, and serve as a foundation for programming assignments with automated grading.
By Bernd Frauenknecht, Emma Cramer, Artur Eisele, Paul Kruse, Lukas Kesper, Jonas Hertrampf, Ramil Sabirov, Jyotirmaya Patra, Johannes Berger, Paul Brunzema, Friedrich Solowjow, Sebastian Trimpe
Reinforcement learning (RL) is an exciting concept as well as a remarkable success story worth sharing. However, RL builds on rather complex interactions between different objects that play out over s...
arXiv:2201. 05000v3 Announce Type: replace-cross Abstract: Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes.
By Reza Refaei Afshar, Joaquin Vanschoren, Uzay Kaymak, Rui Zhang, Yaoxin Wu, Wen Song, Yingqian Zhang
The paper introduces a set of software packages in R, Python, Julia, and C++ that solve the Sorted L-One Penalized Estimation (SLOPE) problem efficiently. The packages employ a hybrid coordinate descent algorithm capable of fitting generalized linear models with various loss functions such as Gaussian, binomial, Poisson, and multinomial logistic regression. They support dense, sparse, and out‑of‑memory data structures, can compute the full SLOPE path, perform cross‑validation (including relaxed SLOPE), and are shown to outperform existing SLOPE implementations in speed on both real and simulated data.
By Johan Larsson, Malgorzata Bogdan, Krystyna Grzesiak, Mathurin Massias, Jonas Wallin
arXiv:2602. 07832v3 Announce Type: replace-cross Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking.
By Xian Wu, Kaijie Zhu, Ying Zhang, Lun Wang, Wenbo Guo
arXiv:2509. 11259v2 Announce Type: replace-cross Abstract: Recent advancements in machine learning have largely been driven by foundation models (FMs) trained on large, diverse datasets, enabling them to generalize effectively to new, related tasks.
By David Schiff, Ofir Lindenbaum, Yonathan Efroni
arXiv:2601. 23075v2 Announce Type: replace Abstract: On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative.
By Yuexin Bian, Jie Feng, Tao Wang, Yijiang Li, Sicun Gao, Yuanyuan Shi
arXiv:2601. 00728v5 Announce Type: replace Abstract: We propose a reinforcement learning (RL) framework for \xy{responsive} precision tuning for linear solvers, which can be extended to general algorithms.
By Erin Carson, Xinye Chen
arXiv:2609. 08136v1 Announce Type: new Abstract: This paper introduces rlaopt, a PyTorch-based package for large-scale optimization and scientific computing using randomized numerical linear algebra (RandNLA).
By Pratik Rathore, Zachary Frangella, Parth Nobel, Xuning Hu, Madeleine Udell
AutoOR is a scalable synthetic data generation and reinforcement learning pipeline that trains large language models to autoformalize operations research problems expressed in natural language across linear, mixed‑integer, and non‑linear categories. By generating verified training data from standard optimization forms and using solver execution feedback as a reward signal, AutoOR enables post‑training of an 8B model to achieve state‑of‑the‑art or competitive results on six established OR benchmarks, matching significantly larger frontier models. For non‑linear problems involving physical dynamics, a curriculum RL strategy bootstraps from limited initial data, making this class tractable for post‑training.
By Sumeet Ramesh Motwani, Chuan Du, Aleksander Petrov, Christopher Davis, Philip Torr, Antonio Papania-Davis, Weishi Yan
arXiv:2606. 30328v1 Announce Type: cross Abstract: Rapid prototyping of algorithms is a critical step in modern machine learning.
By Disha Hegde, Jon Cockayne, Chris. J. Oates