English
Related papers

Related papers: In-context Exploration-Exploitation for Reinforcem…

200 papers

Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these findings by asking why a model learns these disparate…

Machine Learning · Computer Science 2025-06-27 Daniel Wurgaft , Ekdeep Singh Lubana , Core Francisco Park , Hidenori Tanaka , Gautam Reddy , Noah D. Goodman

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to…

Machine Learning · Computer Science 2019-09-10 Lior Shani , Yonathan Efroni , Shie Mannor

Reinforcement learning control algorithms face significant challenges due to out-of-distribution and inefficient exploration problems. While model-based reinforcement learning enhances the agent's reasoning and planning capabilities by…

Machine Learning · Computer Science 2025-03-19 Sunbowen Lee , Yicheng Gong , Chao Deng

This paper develops a fast numerical dual control for exploration and exploitation (DCEE) method to address auto-optimization problems in unknown environments. In auto-optimization problems, the optimal operating condition is unknown a…

Robotics · Computer Science 2026-05-22 Shiying Dong , Haoyang Yang , Qiwei Liu , Wen-Hua Chen

This paper proposes an online tree-based Bayesian approach for reinforcement learning. For inference, we employ a generalised context tree model. This defines a distribution on multivariate Gaussian piecewise-linear models, which can be…

Machine Learning · Statistics 2014-05-05 Nikolaos Tziortziotis , Christos Dimitrakakis , Konstantinos Blekas

Effective exploration is crucial to discovering optimal strategies for multi-agent reinforcement learning (MARL) in complex coordination tasks. Existing methods mainly utilize intrinsic rewards to enable committed exploration or use…

Machine Learning · Computer Science 2024-03-04 Zeyang Liu , Lipeng Wan , Xinrui Yang , Zhuoran Chen , Xingyu Chen , Xuguang Lan

A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly different test environment. A common approach to improve…

Robotics · Computer Science 2019-07-30 Wenxuan Zhou , Lerrel Pinto , Abhinav Gupta

All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient…

Machine Learning · Computer Science 2018-04-05 Trevor Barron , Oliver Obst , Heni Ben Amor

Exploration is essential in reinforcement learning, particularly in environments where external rewards are sparse. Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with…

Machine Learning · Computer Science 2024-01-26 Changmin Yu , Neil Burgess , Maneesh Sahani , Samuel J. Gershman

Information extraction (IE) has been studied extensively. The existing methods always follow a fixed extraction order for complex IE tasks with multiple elements to be extracted in one instance such as event extraction. However, we conduct…

Computation and Language · Computer Science 2024-03-26 Wenhao Huang , Jiaqing Liang , Zhixu Li , Yanghua Xiao , Chuanjun Ji

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning…

Machine Learning · Computer Science 2025-02-13 Amir Moeini , Jiuqi Wang , Jacob Beck , Ethan Blaser , Shimon Whiteson , Rohan Chandra , Shangtong Zhang

Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of tasks, leading to an apparent consensus that ICE optimization…

Computation and Language · Computer Science 2024-06-07 Pragya Srivastava , Satvik Golechha , Amit Deshpande , Amit Sharma

In-context reinforcement learning (ICRL) leverages the in-context learning capabilities of transformer models (TMs) to efficiently generalize to unseen sequential decision-making tasks without parameter updates. However, existing ICRL…

Machine Learning · Computer Science 2026-02-10 Juncheng Dong , Bowen He , Moyang Guo , Ethan X. Fang , Zhuoran Yang , Vahid Tarokh

In-context learning is a powerful capability of certain machine learning models that arguably underpins the success of today's frontier AI models. However, in-context learning is critically limited to settings where the in-context…

Machine Learning · Computer Science 2024-06-19 Rylan Schaeffer , Mikail Khona , Sanmi Koyejo

Contextual bandit problems are a natural fit for many information retrieval tasks, such as learning to rank, text classification, recommendation, etc. However, existing learning methods for contextual bandit problems have one of two…

Information Retrieval · Computer Science 2020-02-06 Rolf Jagerman , Ilya Markov , Maarten de Rijke

Efficiently tackling multiple tasks within complex environment, such as those found in robot manipulation, remains an ongoing challenge in robotics and an opportunity for data-driven solutions, such as reinforcement learning (RL).…

Robotics · Computer Science 2024-04-03 Carlos Plou , Ana C. Murillo , Ruben Martinez-Cantin

Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation…

Machine Learning · Computer Science 2022-10-19 Zhao-Heng Yin , Weirui Ye , Qifeng Chen , Yang Gao

The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient…

Machine Learning · Computer Science 2025-12-09 Caleb Ju , Guanghui Lan

Large Language Models (LLMs) have shown promising in-context learning abilities. However, conventional In-Context Learning (ICL) approaches are often impeded by length limitations of transformer architecture, which pose challenges when…

Computation and Language · Computer Science 2024-03-27 Jianlin Su , Murtadha Ahmed , Wenbo , Luo Ao , Mingren Zhu , Yunfeng Liu

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic perspective by investigating simple binary…

Machine Learning · Computer Science 2026-03-13 Faris Chaudhry , Siddhant Gadkari