English
Related papers

Related papers: Geometric Entropic Exploration

200 papers

This paper proposes \emph{Episodic and Lifelong Exploration via Maximum ENTropy} (ELEMENT), a novel, multiscale, intrinsically motivated reinforcement learning (RL) framework that is able to explore environments without using any extrinsic…

Machine Learning · Computer Science 2024-12-06 Hongming Li , Shujian Yu , Bin Liu , Jose C. Principe

In the maximum state entropy exploration framework, an agent interacts with a reward-free environment to learn a policy that maximizes the entropy of the expected state visitations it is inducing. Hazan et al. (2019) noted that the class of…

Machine Learning · Computer Science 2022-07-11 Mirco Mutti , Riccardo De Santi , Marcello Restelli

Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the…

Machine Learning · Statistics 2018-08-06 Zi Wang , Stefanie Jegelka

Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment. To tackle this problem, we introduce a new technique called…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Adam Pardyl , Grzegorz Rypeść , Grzegorz Kurzejamski , Bartosz Zieliński , Tomasz Trzciński

Exploration is a crucial and distinctive aspect of reinforcement learning (RL) that remains a fundamental open problem. Several methods have been proposed to tackle this challenge. Commonly used methods inject random noise directly into the…

Machine Learning · Computer Science 2024-11-06 Sebastian Griesbach , Carlo D'Eramo

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…

Machine Learning · Computer Science 2020-02-10 Chi Jin , Akshay Krishnamurthy , Max Simchowitz , Tiancheng Yu

Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing large language model (LLM) reasoning, most methods lean toward exploitation, and increasingly encounter…

Computation and Language · Computer Science 2025-11-11 Daixuan Cheng , Shaohan Huang , Xuekai Zhu , Bo Dai , Wayne Xin Zhao , Zhenliang Zhang , Furu Wei

Entropy regularization is a standard technique in reinforcement learning (RL) to enhance exploration, yet it yields negligible effects or even degrades performance in Large Language Models (LLMs). We attribute this failure to the cumulative…

Computation and Language · Computer Science 2026-02-04 Chao Huang , Yujing Lu , Quangang Li , Shenghe Wang , Yan Wang , Yueyang Zhang , Long Xia , Jiashu Zhao , Zhiyuan Sun , Daiting Shi , Tingwen Liu

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…

Although the existing max-value entropy search (MES) is based on the widely celebrated notion of mutual information, its empirical performance can suffer due to two misconceptions whose implications on the exploration-exploitation trade-off…

Machine Learning · Computer Science 2022-03-01 Quoc Phong Nguyen , Bryan Kian Hsiang Low , Patrick Jaillet

LLM pre-training efficacy increasingly depends on data composition rather than sheer volume. Yet, optimal mixing is hindered by categorization flaws: human taxonomies suffer from ontological misalignment, and Euclidean clustering fails to…

Machine Learning · Computer Science 2026-05-27 Yue Min , Ziyun Qiao , Ruining Chen , Yujun Li

In a reward-free environment, what is a suitable intrinsic objective for an agent to pursue so that it can learn an optimal task-agnostic exploration policy? In this paper, we argue that the entropy of the state distribution induced by…

Machine Learning · Computer Science 2021-03-02 Mirco Mutti , Lorenzo Pratissoli , Marcello Restelli

This paper explores the use of Maximum Causal Entropy Inverse Reinforcement Learning (IRL) within the context of discrete-time stationary Mean-Field Games (MFGs) characterized by finite state spaces and an infinite-horizon,…

Systems and Control · Electrical Eng. & Systems 2025-07-22 Berkay Anahtarci , Can Deha Kariksiz , Naci Saldi

Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic…

Machine Learning · Computer Science 2019-06-14 Hyoungseok Kim , Jaekyeom Kim , Yeonwoo Jeong , Sergey Levine , Hyun Oh Song

In online reinforcement learning (online RL), balancing exploration and exploitation is crucial for finding an optimal policy in a sample-efficient way. To achieve this, existing sample-efficient online RL algorithms typically consist of…

Machine Learning · Computer Science 2023-10-26 Zhihan Liu , Miao Lu , Wei Xiong , Han Zhong , Hao Hu , Shenao Zhang , Sirui Zheng , Zhuoran Yang , Zhaoran Wang

We report on an improvement to the implementation of the Maximum Entropy Method (MEM). It amounts to departing from the search space obtained through a singular value decomposition (SVD) of the Kernel. Based on the shape of the SVD basis…

Computational Physics · Physics 2015-03-20 Alexander Rothkopf

In reinforcement learning (RL), an agent must explore an initially unknown environment in order to learn a desired behaviour. When RL agents are deployed in real world environments, safety is of primary concern. Constrained Markov decision…

Machine Learning · Computer Science 2022-06-24 David M. Bossens , Nicholas Bishop

Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO) consistently…

Artificial Intelligence · Computer Science 2026-04-20 Chen Wang , Lai Wei , Yanzhi Zhang , Chenyang Shao , Zedong Dan , Weiran Huang , Ge Lan , Yue Wang

A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek…

Machine Learning · Computer Science 2021-01-15 Riley Simmons-Edler , Ben Eisner , Daniel Yang , Anthony Bisulco , Eric Mitchell , Sebastian Seung , Daniel Lee

Recent works have studied *state entropy maximization* in reinforcement learning, in which the agent's objective is to learn a policy inducing high entropy over states visitation (Hazan et al., 2019). They typically assume full…

Machine Learning · Computer Science 2024-06-05 Riccardo Zamboni , Duilio Cirino , Marcello Restelli , Mirco Mutti