English
Related papers

Related papers: In-Context Compositional Q-Learning for Offline Re…

200 papers

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

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are…

Machine Learning · Statistics 2022-07-28 Chengchun Shi , Shikai Luo , Yuan Le , Hongtu Zhu , Rui Song

While in-context learning (ICL) has achieved remarkable success in natural language and vision domains, its theoretical understanding-particularly in the context of structured geometric data-remains unexplored. This paper initiates a…

Machine Learning · Computer Science 2026-05-19 Zhaiming Shen , Alexander Hsu , Rongjie Lai , Wenjing Liao

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

Machine Learning · Computer Science 2024-09-27 Tong Yang , Yu Huang , Yingbin Liang , Yuejie Chi

The transformer architecture, which processes sequences of input tokens to produce outputs for query tokens, has revolutionized numerous areas of machine learning. A defining feature of transformers is their ability to perform previously…

Machine Learning · Computer Science 2025-10-02 Hongbo Li , Lingjie Duan , Yingbin Liang

In-context learning (ICL), the remarkable ability to solve a task from only input exemplars, is often assumed to be a unique hallmark of Transformer models. By examining commonly employed synthetic ICL tasks, we demonstrate that multi-layer…

Machine Learning · Computer Science 2025-02-26 William L. Tong , Cengiz Pehlevan

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the performance due to the lack of exploration. To overcome it,…

Machine Learning · Computer Science 2024-07-23 Kai Zhao , Jianye Hao , Yi Ma , Jinyi Liu , Yan Zheng , Zhaopeng Meng

This correspondence considers the resource allocation problem in wireless interference channel (IC) under link outage constraints. Since the optimization problem is non-convex in nature, existing approaches to find the optimal power…

Networking and Internet Architecture · Computer Science 2022-03-08 Saniul Alam , Sadia Islam , Muhammad R. A. Khandaker , Risala T. Khan , Faisal Tariq , Apriana Toding

In-context learning (ICL) exhibits dual operating modes: task learning, i.e., acquiring a new skill from in-context samples, and task retrieval, i.e., locating and activating a relevant pretrained skill. Recent theoretical work investigates…

Machine Learning · Computer Science 2024-08-05 Ziqian Lin , Kangwook Lee

Contextual combinatorial optimization (CCO) plays a critical role in decision-making under uncertainty, yet remains a significant challenge. We present Quantum End-to-End Learning (QEL), the first quantum computing-based end-to-end learning…

Quantum Physics · Physics 2026-05-21 Jaehwan Lee , Changhyun Kwon

Large-scale neural language models exhibit a remarkable capacity for in-context learning (ICL): they can infer novel functions from datasets provided as input. Most of our current understanding of when and how ICL arises comes from LMs…

Computation and Language · Computer Science 2024-01-31 Ekin Akyürek , Bailin Wang , Yoon Kim , Jacob Andreas

This paper introduces a novel reinforcement learning (RL) framework, termed Reward-Guided Conservative Q-learning (RG-CQL), to enhance coordination between ride-pooling and public transit within a multimodal transportation network. We model…

Machine Learning · Computer Science 2025-01-27 Yulong Hu , Tingting Dong , Sen Li

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

Computation and Language · Computer Science 2025-11-11 Baturay Saglam , Xinyang Hu , Zhuoran Yang , Dionysis Kalogerias , Amin Karbasi

In-context learning (ICL) refers to the ability of a model to condition on a few in-context demonstrations (input-output examples of the underlying task) to generate the answer for a new query input, without updating parameters. Despite the…

Machine Learning · Computer Science 2023-12-01 Yongqiang Chen , Binghui Xie , Kaiwen Zhou , Bo Han , Yatao Bian , James Cheng

We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in…

Machine Learning · Computer Science 2021-05-07 Lanqing Li , Rui Yang , Dijun Luo

Designing a competent meta-reinforcement learning (meta-RL) algorithm in terms of data usage remains a central challenge to be tackled for its successful real-world applications. In this paper, we propose a sample-efficient meta-RL…

Machine Learning · Computer Science 2023-12-12 Jaeuk Shin , Giho Kim , Howon Lee , Joonho Han , Insoon Yang

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…

Machine Learning · Computer Science 2026-02-04 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Offline reinforcement learning (RL) is a compelling framework for learning optimal policies from past experiences without additional interaction with the environment. Nevertheless, offline RL inevitably faces the problem of distributional…

Machine Learning · Computer Science 2024-04-09 Yeda Song , Dongwook Lee , Gunhee Kim