English
Related papers

Related papers: Disentangling Exploration of Large Language Models…

200 papers

We evaluate language models on their ability to explore interactive environments under a limited interaction budget. We introduce three parametric tasks with controllable exploration difficulty, spanning continuous and discrete…

Machine Learning · Computer Science 2026-02-02 Mahdi JafariRaviz , Keivan Rezaei , Arshia Soltani Moakhar , Zahra Sodagar , Yize Cheng , Soheil Feizi

We investigate the extent to which contemporary Large Language Models (LLMs) can engage in exploration, a core capability in reinforcement learning and decision making. We focus on native performance of existing LLMs, without training…

Machine Learning · Computer Science 2024-10-30 Akshay Krishnamurthy , Keegan Harris , Dylan J. Foster , Cyril Zhang , Aleksandrs Slivkins

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during…

Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on…

Machine Learning · Computer Science 2020-10-13 Pierre Ménard , Omar Darwiche Domingues , Anders Jonsson , Emilie Kaufmann , Edouard Leurent , Michal Valko

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward problems, the reward is rare, which means that the agent will…

Machine Learning · Computer Science 2022-05-03 Pawel Ladosz , Lilian Weng , Minwoo Kim , Hyondong Oh

Achieving effective test-time scaling requires models to engage in In-Context Exploration -- the intrinsic ability to generate, verify, and refine multiple reasoning hypotheses within a single continuous context. Grounded in State Coverage…

Computation and Language · Computer Science 2026-02-13 Futing Wang , Jianhao Yan , Yun Luo , Ganqu Cui , Zhi Wang , Xiaoye Qu , Yue Zhang , Yu Cheng , Tao Lin

Recent advances in vision-language learning have achieved notable success on complete-information question-answering datasets through the integration of extensive world knowledge. Yet, most models operate passively, responding to questions…

Artificial Intelligence · Computer Science 2023-11-06 Manjie Xu , Guangyuan Jiang , Wei Liang , Chi Zhang , Yixin Zhu

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

Representation learning and exploration are among the key challenges for any deep reinforcement learning agent. In this work, we provide a singular value decomposition based method that can be used to obtain representations that preserve…

Machine Learning · Computer Science 2023-05-03 Yash Chandak , Shantanu Thakoor , Zhaohan Daniel Guo , Yunhao Tang , Remi Munos , Will Dabney , Diana L Borsa

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This…

Machine Learning · Computer Science 2026-03-24 Xixi Wu , Qianguo Sun , Ruiyang Zhang , Chao Song , Junlong Wu , Yiyan Qi , Hong Cheng

Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for exploring such environments is to introduce some "intrinsic"…

Machine Learning · Computer Science 2020-07-16 Neale Ratzlaff , Qinxun Bai , Li Fuxin , Wei Xu

The ability to explore efficiently and effectively is a central challenge of reinforcement learning. In this work, we consider exploration through the lens of information theory. Specifically, we cast exploration as a problem of maximizing…

Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning or decision-making abilities through well-designed prompt…

Artificial Intelligence · Computer Science 2024-04-12 Xu Huang , Weiwen Liu , Xiaolong Chen , Xingmei Wang , Defu Lian , Yasheng Wang , Ruiming Tang , Enhong Chen

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

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

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…

Machine Learning · Computer Science 2025-04-15 Anthony GX-Chen , Kenneth Marino , Rob Fergus

Efficient exploration is a well known problem in deep reinforcement learning and this problem is exacerbated in multi-agent reinforcement learning due the intrinsic complexities of such algorithms. There are several approaches to…

Artificial Intelligence · Computer Science 2025-07-11 Ashish Kumar

Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic…

Machine Learning · Computer Science 2025-03-12 Jasmine Bayrooti , Carl Henrik Ek , Amanda Prorok

The goal of meta-reinforcement learning (meta-RL) is to build agents that can quickly learn new tasks by leveraging prior experience on related tasks. Learning a new task often requires both exploring to gather task-relevant information and…

Machine Learning · Computer Science 2021-11-15 Evan Zheran Liu , Aditi Raghunathan , Percy Liang , Chelsea Finn