English
Related papers

Related papers: Balancing Expressivity and Robustness: Constrained…

200 papers

Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge…

Machine Learning · Computer Science 2022-09-23 James Harrison , Luke Metz , Jascha Sohl-Dickstein

Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as…

Machine Learning · Computer Science 2026-04-24 Sukesh Subaharan

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Software Engineering · Computer Science 2025-10-08 Yu Zhu

Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during…

Computation and Language · Computer Science 2025-12-09 Charlie Zhang , Graham Neubig , Xiang Yue

Random Recurrent Neural Networks (RRNN) are the simplest recurrent networks to model and extract features from sequential data. The simplicity however comes with a price; RRNN are known to be susceptible to diminishing/exploding gradient…

Machine Learning · Computer Science 2025-06-10 Yang Zheng , Eli Shlizerman

A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered…

Machine Learning · Computer Science 2023-10-05 Evgenii Nikishin , Junhyuk Oh , Georg Ostrovski , Clare Lyle , Razvan Pascanu , Will Dabney , André Barreto

Multi-task reinforcement learning (MTRL) aims to endow a single agent with the ability to perform well on multiple tasks. Recent works have focused on developing novel sophisticated architectures to improve performance, often resulting in…

Machine Learning · Computer Science 2025-03-13 Reginald McLean , Evangelos Chatzaroulas , Jordan Terry , Isaac Woungang , Nariman Farsad , Pablo Samuel Castro

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

Robotics · Computer Science 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representations, which break down complex state and action spaces into…

Machine Learning · Computer Science 2024-09-20 Panayiotis Panayiotou , Özgür Şimşek

Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…

Machine Learning · Statistics 2019-06-17 Elena Smirnova , Elvis Dohmatob , Jérémie Mary

Operating under real world conditions is challenging due to the possibility of a wide range of failures induced by execution errors and state uncertainty. In relatively benign settings, such failures can be overcome by retrying or executing…

Robotics · Computer Science 2023-03-10 Shivam Vats , Maxim Likhachev , Oliver Kroemer

We study stochastic optimization in the context of performative shifts, where the data distribution changes in response to the deployed model. We demonstrate that naive retraining can be provably suboptimal even for simple distribution…

Machine Learning · Computer Science 2024-08-19 Anmol Kabra , Kumar Kshitij Patel

The widespread adoption of transfer learning has revolutionized machine learning by enabling efficient adaptation of pre-trained models to new domains. However, the reliability of these adaptations remains poorly understood, particularly…

Machine Learning · Computer Science 2025-09-01 Prabhav Singh , Jessica Sorrell

Model-Free Reinforcement Learning has achieved meaningful results in stable environments but, to this day, it remains problematic in regime changing environments like financial markets. In contrast, model-based RL is able to capture some…

Machine Learning · Computer Science 2021-04-23 Eric Benhamou , David Saltiel , Serge Tabachnik , Sui Kai Wong , François Chareyron

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this…

Machine Learning · Computer Science 2024-03-01 Clare Lyle , Zeyu Zheng , Khimya Khetarpal , Hado van Hasselt , Razvan Pascanu , James Martens , Will Dabney

Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier…

Machine Learning · Computer Science 2026-05-07 Yu Huang , Zixin Wen , Yuejie Chi , Yuting Wei , Aarti Singh , Yingbin Liang , Yuxin Chen

Reinforcement Learning (RL) has been widely applied to many control tasks and substantially improved the performances compared to conventional control methods in many domains where the reward function is well defined. However, for many…

Machine Learning · Computer Science 2024-03-22 Baohe Zhang , Yuan Zhang , Lilli Frison , Thomas Brox , Joschka Bödecker

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in…

Machine Learning · Computer Science 2025-02-25 Austin Coursey , Marcos Quinones-Grueiro , Gautam Biswas

Task and motion planning (TAMP) for robotics manipulation necessitates long-horizon reasoning involving versatile actions and skills. While deterministic actions can be crafted by sampling or optimizing with certain constraints, planning…

Robotics · Computer Science 2025-10-17 Gaoyuan Liu , Joris de Winter , Yuri Durodie , Denis Steckelmacher , Ann Nowe , Bram Vanderborght

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

‹ Prev 1 4 5 6 7 8 10 Next ›