English
Related papers

Related papers: Transformers Provably Implement In-Context Reinfor…

200 papers

Safe reinforcement learning (Safe RL) aims to ensure policy performance while satisfying safety constraints. However, most existing Safe RL methods assume benign environments, making them vulnerable to adversarial perturbations commonly…

Machine Learning · Computer Science 2026-02-19 Jialiang Fan , Shixiong Jiang , Mengyu Liu , Fanxin Kong

Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with…

Robotics · Computer Science 2024-12-18 Jiaxu Xing , Ismail Geles , Yunlong Song , Elie Aljalbout , Davide Scaramuzza

Real-time path planning in constrained environments remains a fundamental challenge for autonomous systems. Traditional classical planners, while effective under perfect perception assumptions, are often sensitive to real-world perception…

Robotics · Computer Science 2026-02-02 Feng Tao , Luca Paparusso , Chenyi Gu , Robin Koehler , Chenxu Wu , Xinyu Huang , Christian Juette , David Paz , Ren Liu

The intrinsic high dimension of fluid dynamics is an inherent challenge to control of aerodynamic flows, and this is further complicated by a flow's nonlinear response to strong disturbances. Deep reinforcement learning, which takes…

Fluid Dynamics · Physics 2025-07-28 Zhecheng Liu , Diederik Beckers , Jeff D. Eldredge

As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions…

Robotics · Computer Science 2026-04-10 Haruto Nagahisa , Kohei Matsumoto , Yuki Tomita , Yuki Hyodo , Ryo Kurazume

Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…

Machine Learning · Computer Science 2025-03-18 Wei Hung , Shao-Hua Sun , Ping-Chun Hsieh

In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks by leveraging past experiences as context, without updating their parameters. Recent approaches train…

Machine Learning · Computer Science 2025-09-30 Wenhao Zhang , Shao Zhang , Xihuai Wang , Yang Li , Ying Wen

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…

Robotics · Computer Science 2026-03-10 Toan Nguyen , Weiduo Yuan , Songlin Wei , Hui Li , Daniel Seita , Yue Wang

In-context learning (ICL) enables transformers to adapt to new tasks through contextual examples without parameter updates. While existing research has typically studied ICL in fixed-complexity environments, practical language models…

Machine Learning · Computer Science 2025-06-25 Puneesh Deora , Bhavya Vasudeva , Tina Behnia , Christos Thrampoulidis

Transformer models (TMs) have exhibited remarkable in-context reinforcement learning (ICRL) capabilities, allowing them to generalize to and improve in previously unseen environments without re-training or fine-tuning. This is typically…

Machine Learning · Computer Science 2025-05-22 Weiqin Chen , Xinjie Zhang , Dharmashankar Subramanian , Santiago Paternain

Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging. This paper presents a Transformer model that can provably approximate and opt for domain adaptation methods for a given dataset in…

Machine Learning · Computer Science 2024-05-28 Ryuichiro Hataya , Kota Matsui , Masaaki Imaizumi

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2021-07-06 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

Going beyond mimicking limited human experiences, recent studies show initial evidence that, like humans, large language models (LLMs) are capable of improving their abilities purely by self-correction, i.e., correcting previous responses…

Machine Learning · Computer Science 2024-11-19 Yifei Wang , Yuyang Wu , Zeming Wei , Stefanie Jegelka , Yisen Wang

Choosing an appropriate parameter set for the designed controller is critical for the final performance but usually requires a tedious and careful tuning process, which implies a strong need for automatic tuning methods. However, among…

Systems and Control · Electrical Eng. & Systems 2022-09-13 Yuheng Lei , Jianyu Chen , Shengbo Eben Li , Sifa Zheng

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

Understanding the internal mechanisms of GPT-style transformers, particularly their capacity to perform in-context learning (ICL), is critical for advancing AI alignment and interpretability. In-context learning allows transformers to…

Machine Learning · Computer Science 2024-10-24 Samarth Bhargav , Alexander Gu

Offline reinforcement learning (RL) suffers from the distribution shift between the offline dataset and the online environment. In multi-agent RL (MARL), this distribution shift may arise from the nonstationary opponents in the online…

Machine Learning · Computer Science 2025-02-25 Tao Li , Juan Guevara , Xinhong Xie , Quanyan Zhu

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able…

Machine Learning · Computer Science 2022-09-28 Desik Rengarajan , Sapana Chaudhary , Jaewon Kim , Dileep Kalathil , Srinivas Shakkottai

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…

Pre-trained large language models (LLMs) based on Transformer have demonstrated striking in-context learning (ICL) abilities. With a few demonstration input-label pairs, they can predict the label for an unseen input without any parameter…

Machine Learning · Computer Science 2024-10-15 Xinhao Yao , Xiaolin Hu , Shenzhi Yang , Yong Liu