English
Related papers

Related papers: Latent Q-Barrier Shielding for Safe In-Context Rei…

200 papers

Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. However, it is unclear where this capability comes from as there…

Computation and Language · Computer Science 2024-02-21 Yanda Chen , Chen Zhao , Zhou Yu , Kathleen McKeown , He He

Offline reinforcement learning (RL) enables training from fixed data without online interaction, but policies learned offline often struggle when deployed in dynamic environments due to distributional shift and unreliable value estimates on…

Machine Learning · Computer Science 2025-11-06 Lipeng Zu , Hansong Zhou , Xiaonan Zhang

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Machine Learning · Computer Science 2025-12-04 Runze Zhao , Yue Yu , Ruhan Wang , Chunfeng Huang , Dongruo Zhou

Offline safe RL is of great practical relevance for deploying agents in real-world applications. However, acquiring constraint-satisfying policies from the fixed dataset is non-trivial for conventional approaches. Even worse, the learned…

Machine Learning · Computer Science 2023-01-31 Qin Zhang , Linrui Zhang , Haoran Xu , Li Shen , Bowen Wang , Yongzhe Chang , Xueqian Wang , Bo Yuan , Dacheng Tao

While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive…

Machine Learning · Computer Science 2026-01-27 Yibo Li , Zijie Lin , Ailin Deng , Xuan Zhang , Yufei He , Shuo Ji , Tri Cao , Bryan Hooi

Offline safe reinforcement learning (RL) has emerged as a promising approach for learning safe behaviors without engaging in risky online interactions with the environment. Most existing methods in offline safe RL rely on cost constraints…

Machine Learning · Computer Science 2025-04-22 Ze Gong , Akshat Kumar , Pradeep Varakantham

We formalize a new concept for LLMs, context-enhanced learning. It involves standard gradient-based learning on text except that the context is enhanced with additional data on which no auto-regressive gradients are computed. This setting…

Machine Learning · Computer Science 2025-06-06 Xingyu Zhu , Abhishek Panigrahi , Sanjeev Arora

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

Artificial Intelligence · Computer Science 2019-11-26 Nils Jansen , Bettina Könighofer , Sebastian Junges , Alexandru C. Serban , Roderick Bloem

An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great…

Artificial Intelligence · Computer Science 2022-02-28 Wei Gao , David Hsu , Wee Sun Lee

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

Artificial Intelligence · Computer Science 2026-02-18 Ankit Sharma , Nachiket Tapas , Jyotiprakash Patra

In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…

Systems and Control · Electrical Eng. & Systems 2023-05-02 Lunet Yifru , Ali Baheri

This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and…

Machine Learning · Computer Science 2026-04-28 Hanna Rød , Dagny Streit , Nils Valseth Selte , Justin Li

In-context learning (ICL) improves language models' performance on a variety of NLP tasks by simply demonstrating a handful of examples at inference time. It is not well understood why ICL ability emerges, as the model has never been…

Computation and Language · Computer Science 2023-06-28 Xiaochuang Han , Daniel Simig , Todor Mihaylov , Yulia Tsvetkov , Asli Celikyilmaz , Tianlu Wang

Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow learning from contextual information. Humans use context to…

Machine Learning · Computer Science 2023-10-17 Francisco Munguia-Galeano , Ah-Hwee Tan , Ze Ji

We argue that in-context learning (ICL) predictably arises from standard self-supervised next-token pretraining, rather than being an exotic emergent property. This work establishes the foundational principles of this emergence by focusing…

Machine Learning · Computer Science 2025-07-15 Paul M. Riechers , Henry R. Bigelow , Eric A. Alt , Adam Shai

With the emergence of large language models, such as LLaMA and OpenAI GPT-3, In-Context Learning (ICL) gained significant attention due to its effectiveness and efficiency. However, ICL is very sensitive to the choice, order, and verbaliser…

Computation and Language · Computer Science 2024-10-10 Simon Yu , Jie He , Pasquale Minervini , Jeff Z. Pan

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Machine Learning · Computer Science 2024-02-06 Xinglong Zhang , Yaoqian Peng , Biao Luo , Wei Pan , Xin Xu , Haibin Xie

Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the sense that they…

Artificial Intelligence · Computer Science 2026-02-23 Tiberiu-Andrei Georgescu , Alexander W. Goodall , Dalal Alrajeh , Francesco Belardinelli , Sebastian Uchitel

Offline inverse reinforcement learning (IRL) aims to recover a reward function that explains expert behavior using only fixed demonstration data, without any additional online interaction. We propose BiCQL-ML, a policy-free offline IRL…

Machine Learning · Computer Science 2025-12-01 Junsung Park

Interactive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in…

Artificial Intelligence · Computer Science 2018-07-27 Francisco Cruz , German I. Parisi , Stefan Wermter