English
Related papers

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

200 papers

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling…

Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints that expert agents adhere to, based on their demonstration data. As an emerging research topic, ICRL has received considerable attention in…

Machine Learning · Computer Science 2025-02-04 Guiliang Liu , Sheng Xu , Shicheng Liu , Ashish Gaurav , Sriram Ganapathi Subramanian , Pascal Poupart

Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when…

Computation and Language · Computer Science 2025-06-11 Gouki Minegishi , Hiroki Furuta , Shohei Taniguchi , Yusuke Iwasawa , Yutaka Matsuo

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

In this paper, we conduct a comprehensive study of In-Context Learning (ICL) by addressing several open questions: (a) What type of ICL estimator is learned by large language models? (b) What is a proper performance metric for ICL and what…

Machine Learning · Statistics 2023-10-11 Yufeng Zhang , Fengzhuo Zhang , Zhuoran Yang , Zhaoran Wang

Transformers can efficiently learn in-context from example demonstrations. Most existing theoretical analyses studied the in-context learning (ICL) ability of transformers for linear function classes, where it is typically shown that the…

Machine Learning · Computer Science 2024-11-06 Kazusato Oko , Yujin Song , Taiji Suzuki , Denny Wu

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical analysis suggesting that adversarially pretrained transformers…

Machine Learning · Computer Science 2026-03-03 Soichiro Kumano , Hiroshi Kera , Toshihiko Yamasaki

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these…

Machine Learning · Computer Science 2025-10-24 Mayank Jobanputra , Yana Veitsman , Yash Sarrof , Aleksandra Bakalova , Vera Demberg , Ellie Pavlick , Michael Hahn

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

Machine Learning · Computer Science 2025-05-16 Jonathan Clifford Balloch

In-context learning (ICL) is the ability of a model to learn a new task by observing a few exemplars in its context. While prevalent in NLP, this capability has recently also been observed in Reinforcement Learning (RL) settings. Prior…

Machine Learning · Computer Science 2025-08-14 Thomas Schmied , Fabian Paischer , Vihang Patil , Markus Hofmarcher , Razvan Pascanu , Sepp Hochreiter

Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL). While theoretical studies, e.g., \cite{zhang2023trained}, attempt to explain the mechanism of ICL, they assume…

Machine Learning · Computer Science 2024-06-19 Yue Xing , Xiaofeng Lin , Chenheng Xu , Namjoon Suh , Qifan Song , Guang Cheng

Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes. However, a challenge that often arises is the trade-off between both the computational efficiency of the…

Machine Learning · Computer Science 2023-08-21 Anthony Kobanda , Valliappan C. A. , Joshua Romoff , Ludovic Denoyer

Large language models (LLMs) like transformers demonstrate impressive in-context learning (ICL) capabilities, allowing them to make predictions for new tasks based on prompt exemplars without parameter updates. While existing ICL theories…

Machine Learning · Computer Science 2024-11-12 Kevin Christian Wibisono , Yixin Wang

In-context learning (ICL) has emerged as a powerful capability of transformer-based language models, enabling them to perform tasks by conditioning on a small number of examples presented at inference time, without any parameter updates.…

Machine Learning · Computer Science 2025-08-15 Jathin Korrapati , Patrick Mendoza , Aditya Tomar , Abein Abraham

We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…

Machine Learning · Computer Science 2026-02-04 Zishi Zhang , Jinhui Han , Ming Hu , Yijie Peng

Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work focuses on the former. Previous methods build the network with several modules like CNN, LSTM and Attention. Recent…

Machine Learning · Computer Science 2023-01-04 Hangyu Mao , Rui Zhao , Hao Chen , Jianye Hao , Yiqun Chen , Dong Li , Junge Zhang , Zhen Xiao

Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updates. However, many interactive settings go beyond static prediction to online…

Machine Learning · Computer Science 2026-05-12 Emile Anand , Abdullah Ateyeh , Xinyuan Cao , Max Dabagia

Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset collected by policies of different expertise levels. It is as simple as supervised learning and Behavior…

Machine Learning · Statistics 2022-10-25 Alexandre Piche , Rafael Pardinas , David Vazquez , Igor Mordatch , Chris Pal

Transformer-based models demonstrate a remarkable ability for in-context learning (ICL), where they can adapt to unseen tasks from a few prompt examples without parameter updates. Recent research has illuminated how Transformers perform…

Machine Learning · Computer Science 2025-10-14 Haoyuan Sun , Ali Jadbabaie , Navid Azizan