English
Related papers

Related papers: When Should We Introduce Safety Interventions Duri…

200 papers

This paper addresses the question of how a previously available control policy $\pi_s$ can be used as a supervisor to more quickly and safely train a new learned control policy $\pi_L$ for a robot. A weighted average of the supervisor and…

Machine Learning · Computer Science 2019-01-23 Yinan Zhang , Devin Balkcom , Haoxiang Li

Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, while large-scale…

Machine Learning · Computer Science 2024-01-08 Xiaoqian Liu , Jianbin Jiao , Junge Zhang

Trained models are often composed with post-hoc transforms such as temperature scaling (TS), ensembling and stochastic weight averaging (SWA) to improve performance, robustness, uncertainty estimation, etc. However, such transforms are…

Machine Learning · Computer Science 2024-10-07 Rishabh Ranjan , Saurabh Garg , Mrigank Raman , Carlos Guestrin , Zachary Lipton

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

Machine Learning · Computer Science 2025-10-07 Zhepeng Cen , Yihang Yao , William Han , Zuxin Liu , Ding Zhao

Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical…

Computers and Society · Computer Science 2017-08-23 Kush R. Varshney , Homa Alemzadeh

Software, while beneficial, poses potential cybersecurity risks due to inherent vulnerabilities. Detecting these vulnerabilities is crucial, and deep learning has shown promise as an effective tool for this task due to its ability to…

Software Engineering · Computer Science 2024-01-17 Imam Nur Bani Yusuf , Lingxiao Jiang

Can a small amount of verified goal information steer the expensive self-supervised pretraining of foundation models? Standard pretraining optimizes a fixed proxy objective (e.g., next-token prediction), which can misallocate compute away…

Machine Learning · Computer Science 2026-01-30 Shuqi Ke , Giulia Fanti

Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a hurdle for its practical application on real robots. To address this issue, safe reinforcement…

Machine Learning · Computer Science 2024-04-29 Maeva Guerrier , Hassan Fouad , Giovanni Beltrame

Reinforcement learning (RL) has become widely adopted in robot control. Despite many successes, one major persisting problem can be very low data efficiency. One solution is interactive feedback, which has been shown to speed up RL…

Robotics · Computer Science 2026-04-29 Daniel Harnack , Julie Pivin-Bachler , Nicolás Navarro-Guerrero

Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…

Machine Learning · Computer Science 2025-02-28 Kaustubh Mani , Vincent Mai , Charlie Gauthier , Annie Chen , Samer Nashed , Liam Paull

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Artificial Intelligence · Computer Science 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

Machine Learning · Computer Science 2025-03-28 Jeonghwan Cheon , Se-Bum Paik

We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal…

Artificial Intelligence · Computer Science 2024-04-23 Kim Hammar , Rolf Stadler

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

Computation and Language · Computer Science 2023-02-17 Tong Guo

Probes trained on model activations can detect undesirable behaviors like deception or biases that are difficult to identify from outputs alone. This makes them useful detectors to identify misbehavior. Furthermore, they are also valuable…

Machine Learning · Computer Science 2025-10-27 Jan Wehner , Mario Fritz

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from that target domain. Finetuning presents two challenges: (i)…

Machine Learning · Computer Science 2025-05-28 Louis Bethune , David Grangier , Dan Busbridge , Eleonora Gualdoni , Marco Cuturi , Pierre Ablin

Gradient-based meta-learning has proven to be highly effective at learning model initializations, representations, and update rules that allow fast adaptation from a few samples. The core idea behind these approaches is to use fast…

Machine Learning · Computer Science 2019-10-07 Khurram Javed , Hengshuai Yao , Martha White

Early exits enable the network's forward pass to terminate early by attaching trainable internal classifiers to the backbone network. Existing early-exit methods typically adopt either a joint training approach, where the backbone and exit…

Robots are more capable of achieving manipulation tasks for everyday activities than before. But the safety of manipulation skills that robots employ is still an open problem. Considering all possible failures during skill learning…

Robotics · Computer Science 2023-05-05 Abdullah Cihan Ak , Eren Erdal Aksoy , Sanem Sariel

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting.…

Machine Learning · Computer Science 2021-03-01 Jianyi Zhang , Paul Weng
‹ Prev 1 8 9 10 Next ›