English
Related papers

Related papers: Context-Former: Stitching via Latent Conditioned S…

200 papers

Recent advancements in language models have demonstrated remarkable in-context learning abilities, prompting the exploration of in-context reinforcement learning (ICRL) to extend the promise to decision domains. Due to involving more…

Artificial Intelligence · Computer Science 2026-02-09 Jinmei Liu , Fuhong Liu , Zhenhong Sun , Jianye Hao , Huaxiong Li , Bo Wang , Daoyi Dong , Chunlin Chen , Zhi Wang

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Computation and Language · Computer Science 2023-12-25 Afra Amini , Massimiliano Ciaramita

Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to learn new language or vision tasks without any weight…

Machine Learning · Computer Science 2023-12-08 Sharath Chandra Raparthy , Eric Hambro , Robert Kirk , Mikael Henaff , Roberta Raileanu

Offline reinforcement learning (RL) enables agents to learn policies from fixed datasets, avoiding costly or unsafe environment interactions. However, its effectiveness is often limited by dataset sparsity and the lack of transition overlap…

Artificial Intelligence · Computer Science 2025-07-22 Lu Guo , Yixiang Shan , Zhengbang Zhu , Qifan Liang , Lichang Song , Ting Long , Weinan Zhang , Yi Chang

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data…

Machine Learning · Computer Science 2025-06-17 Sarthak Mittal , Eric Elmoznino , Leo Gagnon , Sangnie Bhardwaj , Tom Marty , Dhanya Sridhar , Guillaume Lajoie

Traditional offline reinforcement learning (RL) methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of…

Machine Learning · Statistics 2025-07-16 Charles A. Hepburn , Yue Jin , Giovanni Montana

What if artificial intelligence could not only solve problems for which it was trained but also learn to teach itself to solve new problems (i.e., meta-learn)? In this study, we demonstrate that a pre-trained transformer fine-tuned with…

Machine Learning · Computer Science 2025-01-27 Micah Rentschler , Jesse Roberts

Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to…

Machine Learning · Computer Science 2026-03-23 Zhongjian Qiao , Rui Yang , Jiafei Lyu , Chenjia Bai , Xiu Li , Siyang Gao , Shuang Qiu

Reinforcement Learning-based recommender systems (RLRS) offer an effective way to handle sequential recommendation tasks but often face difficulties in real-world settings, where user feedback data can be sub-optimal or sparse. In this…

Information Retrieval · Computer Science 2025-10-16 Xiaocong Chen , Siyu Wang , Lina Yao

Transfer learning based on full fine-tuning (FFT) of the pre-trained encoder and task-specific decoder becomes increasingly complex as deep models grow exponentially. Parameter efficient fine-tuning (PEFT) approaches using adapters…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Hayeon Jo , Hyesong Choi , Minhee Cho , Dongbo Min

The binary exponential backoff scheme is widely used in WiFi 7 and still incurs poor throughput performance under dynamic channel environments. Recent model-based approaches (e.g., non-persistent and $p$-persistent CSMA) simply optimize…

Machine Learning · Computer Science 2025-09-12 Shugang Hao , Hongbo Li , Lingjie Duan

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…

Machine Learning · Computer Science 2023-11-14 Lu Wen , Songan Zhang , H. Eric Tseng , Huei Peng

With the increasing ability of large language models (LLMs), in-context learning (ICL) has evolved as a new paradigm for natural language processing (NLP), where instead of fine-tuning the parameters of an LLM specific to a downstream task…

Information Retrieval · Computer Science 2024-05-03 Andrew Parry , Debasis Ganguly , Manish Chandra

Predicting simple function classes has been widely used as a testbed for developing theory and understanding of the trained Transformer's in-context learning (ICL) ability. In this paper, we revisit the training of Transformers on linear…

Machine Learning · Computer Science 2024-05-27 Shang Liu , Zhongze Cai , Guanting Chen , Xiaocheng Li

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

In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of…

Machine Learning · Computer Science 2025-08-19 Deqian Kong , Dehong Xu , Minglu Zhao , Bo Pang , Jianwen Xie , Andrew Lizarraga , Yuhao Huang , Sirui Xie , Ying Nian Wu

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter…

Machine Learning · Computer Science 2023-05-19 Ekin Akyürek , Dale Schuurmans , Jacob Andreas , Tengyu Ma , Denny Zhou

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

Computation and Language · Computer Science 2024-10-23 Tsachi Blau , Moshe Kimhi , Yonatan Belinkov , Alexander Bronstein , Chaim Baskin

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the…

Artificial Intelligence · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Yaocheng Zhang , Jia Liu , Ke Chen , Dongbin Zhao

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the…

Machine Learning · Computer Science 2023-11-08 Yunkai Gao , Rui Zhang , Jiaming Guo , Fan Wu , Qi Yi , Shaohui Peng , Siming Lan , Ruizhi Chen , Zidong Du , Xing Hu , Qi Guo , Ling Li , Yunji Chen