中文
相关论文

相关论文: KEA: Keeping Exploration Alive by Proactively Coor…

200 篇论文

We present a novel extension to the family of Soft Actor-Critic (SAC) algorithms. We argue that based on the Maximum Entropy Principle, discrete SAC can be further improved via additional statistical constraints derived from a surrogate…

机器学习 · 计算机科学 2025-06-24 Dexter Neo , Tsuhan Chen

Advances in Reinforcement Learning (RL) have demonstrated data efficiency and optimal control over large state spaces at the cost of scalable performance. Genetic methods, on the other hand, provide scalability but depict hyperparameter…

机器学习 · 计算机科学 2021-01-19 Karush Suri , Xiao Qi Shi , Konstantinos N. Plataniotis , Yuri A. Lawryshyn

Tool-augmented LLM systems expose a control regime that learning theory has largely ignored: sequential decision-making with a massive discrete action universe (tools, APIs, documents) in which only a small, unknown subset is relevant for…

人工智能 · 计算机科学 2026-01-14 Angshul Majumdar

Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived from the mismatch…

机器学习 · 计算机科学 2026-05-22 Lily Goli , Justin Kerr , Daniele Reda , Alec Jacobson , Andrea Tagliasacchi , Angjoo Kanazawa

Reinforcement Learning (RL) has made remarkable achievements, but it still suffers from inadequate exploration strategies, sparse reward signals, and deceptive reward functions. To alleviate these problems, a Population-guided Novelty…

机器学习 · 计算机科学 2021-10-12 Qihao Liu , Yujia Wang , Xiaofeng Liu

In this paper, we propose SACHER (soft actor-critic (SAC) with hindsight experience replay (HER)), which constitutes a class of deep reinforcement learning (DRL) algorithms. SAC is known as an off-policy model-free DRL algorithm based on…

系统与控制 · 电气工程与系统科学 2021-06-08 Myoung Hoon Lee , Jun Moon

Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this approach comes at the expense of training instability, caused…

机器学习 · 计算机科学 2024-06-11 Bahareh Tasdighi , Abdullah Akgül , Manuel Haussmann , Kenny Kazimirzak Brink , Melih Kandemir

Curiosity is a general method for augmenting an environment reward with an intrinsic reward, which encourages exploration and is especially useful in sparse reward settings. As curiosity is calculated using next state prediction error, the…

机器学习 · 计算机科学 2021-05-19 Auguste Lehuger , Matthew Crosby

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot…

机器学习 · 计算机科学 2022-03-04 Simone Parisi , Davide Tateo , Maximilian Hensel , Carlo D'Eramo , Jan Peters , Joni Pajarinen

Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-quality trajectories, especially under limited resources.…

机器学习 · 计算机科学 2026-01-29 Jinyang Wu , Shuo Yang , Changpeng Yang , Yuhao Shen , Shuai Zhang , Zhengqi Wen , Jianhua Tao

Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear probing that can explore diverse augmentations, \eg, random…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Qi Qian , Yuanhong Xu , Juhua Hu

Entity Alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) and is an essential step of KG fusion. Current mainstream methods -- neural EA models -- rely on training with seed alignment, i.e., a set of…

计算与语言 · 计算机科学 2021-10-14 Bing Liu , Harrisen Scells , Guido Zuccon , Wen Hua , Genghong Zhao

Sparse reward is one of the biggest challenges in reinforcement learning (RL). In this paper, we propose a novel method called Generative Exploration and Exploitation (GENE) to overcome sparse reward. GENE automatically generates start…

机器学习 · 计算机科学 2019-11-21 Jiechuan Jiang , Zongqing Lu

Solving sparse reward tasks through exploration is one of the major challenges in deep reinforcement learning, especially in three-dimensional, partially-observable environments. Critically, the algorithm proposed in this article uses a…

人工智能 · 计算机科学 2021-06-18 Gabriele Libardi , Gianni De Fabritiis

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and multimodal parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of…

机器学习 · 计算机科学 2024-09-20 Arpan Biswas , Rama Vasudevan , Rohit Pant , Ichiro Takeuchi , Hiroshi Funakubo , Yongtao Liu

Designing protocols enhancing cooperation for multi-agent systems remains a grand challenge. Cheap talk, defined as costless, non-binding communication before formal action, serves as a pivotal solution. However, existing theoretical…

多智能体系统 · 计算机科学 2026-03-03 Zhao Song , Chen Shen , Zhen Wang , The Anh Han

Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging deep reinforcement learning (RL) problems, but are much…

人工智能 · 计算机科学 2018-10-31 Edoardo Conti , Vashisht Madhavan , Felipe Petroski Such , Joel Lehman , Kenneth O. Stanley , Jeff Clune

During recent years, deep reinforcement learning (DRL) has made successful incursions into complex decision-making applications such as robotics, autonomous driving or video games. Off-policy algorithms tend to be more sample-efficient than…

机器学习 · 计算机科学 2021-12-06 Jesus Bujalance Martin , Raphael Chekroun , Fabien Moutarde

Computer use agents represent an emerging area in artificial intelligence, aiming to operate computers autonomously to fulfill user tasks, attracting significant attention from both industry and academia. However, the performance of…

人工智能 · 计算机科学 2026-01-23 Yuhao Cheng , Liang Tang , Shuxian Li , Yukang Huo , Tiaonan Duan , Kaer Huang , Yanzhe Jing , Yiqiang Yan

In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy learning. We propose…

机器学习 · 计算机科学 2025-11-12 Ruochuan Shi , Runyu Lu , Yuanheng Zhu , Dongbin Zhao