English
Related papers

Related papers: Transformers as Decision Makers: Provable In-Conte…

200 papers

The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fine-tuning setting, resulting in a significant performance…

Machine Learning · Computer Science 2025-01-24 Felix den Breejen , Sangmin Bae , Stephen Cha , Se-Young Yun

In coming up with solutions to real-world problems, humans implicitly adhere to constraints that are too numerous and complex to be specified completely. However, reinforcement learning (RL) agents need these constraints to learn the…

Machine Learning · Computer Science 2024-06-25 Sriram Ganapathi Subramanian , Guiliang Liu , Mohammed Elmahgiubi , Kasra Rezaee , Pascal Poupart

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

Machine Learning · Computer Science 2026-05-19 Rushil Chandrupatla , Leo Bangayan , Sebastian Leng

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

System optimal traffic routing can mitigate congestion by assigning routes for a portion of vehicles so that the total travel time of all vehicles in the transportation system can be reduced. However, achieving real-time optimal routing…

Machine Learning · Computer Science 2024-07-11 Zemian Ke , Qiling Zou , Jiachao Liu , Sean Qian

The field of Offline Reinforcement Learning (RL) aims to derive effective policies from pre-collected datasets without active environment interaction. While traditional offline RL algorithms like Conservative Q-Learning (CQL) and Implicit…

Machine Learning · Computer Science 2025-11-21 Ali Murtaza Caunhye , Asad Jeewa

Reinforcement learning (RL) can in principle let robots automatically adapt to new tasks, but current RL methods require a large number of trials to accomplish this. In this paper, we tackle rapid adaptation to new tasks through the…

Deep Reinforcement Learning (DRL) has emerged as an efficient approach to resource allocation due to its strong capability in handling complex decision-making tasks. However, only limited research has explored the training of DRL models…

Machine Learning · Computer Science 2025-09-23 Aohan Li , Miyu Tsuzuki

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

Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error,…

Machine Learning · Computer Science 2022-06-22 Fan-Ming Luo , Tian Xu , Hang Lai , Xiong-Hui Chen , Weinan Zhang , Yang Yu

Decision Transformers (DTs) have emerged as a powerful framework for sequential decision making by formulating offline reinforcement learning (RL) as a sequence modeling problem. However, extending DTs to online settings with pure RL…

Machine Learning · Computer Science 2026-01-05 Junkai Luo , Yinglun Zhu

Pretrained Transformers demonstrate remarkable in-context learning (ICL) capabilities, enabling them to adapt to new tasks from demonstrations without parameter updates. However, theoretical studies often rely on simplified architectures…

Machine Learning · Statistics 2026-02-06 Samet Demir , Zafer Dogan

Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating…

In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in…

Machine Learning · Computer Science 2023-05-29 Kartik Ahuja , David Lopez-Paz

Combinatorial optimization problems like the Traveling Salesman Problem are critical in industry yet NP-hard. Neural Combinatorial Optimization has shown promise, but its reliance on online reinforcement learning (RL) hampers deployment and…

Machine Learning · Computer Science 2026-03-27 Hironori Ohigashi , Shinichiro Hamada

Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings. Recently, a similar surge of using Transformers has appeared in the domain of reinforcement learning (RL), but it is faced…

Machine Learning · Computer Science 2023-09-22 Wenzhe Li , Hao Luo , Zichuan Lin , Chongjie Zhang , Zongqing Lu , Deheng Ye

The emergence of in-context learning (ICL) is potentially attributed to two major abilities: task recognition (TR) for recognizing the task from demonstrations and utilizing pre-trained priors, and task learning (TL) for learning from…

Machine Learning · Computer Science 2024-06-21 Xiaolei Wang , Xinyu Tang , Wayne Xin Zhao , Ji-Rong Wen

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…

Machine Learning · Computer Science 2025-09-11 Lukas Toral , Teddy Lazebnik

We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal…

Machine Learning · Computer Science 2022-11-21 Shiro Takagi

In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL…

Computation and Language · Computer Science 2024-08-26 Haowei Du , Dongyan Zhao