中文
相关论文

相关论文: Demonstration-Guided Reinforcement Learning with E…

200 篇论文

Controlling high-dimensional systems in biological and robotic applications is challenging due to expansive state-action spaces, where effective exploration is critical. Commonly used exploration strategies in reinforcement learning are…

机器学习 · 计算机科学 2026-01-28 Yunyue Wei , Chenhui Zuo , Yanan Sui

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL…

机器学习 · 计算机科学 2021-09-28 Zhaorun Chen , Binhao Chen , Shenghan Xie , Liang Gong , Chengliang Liu , Zhengfeng Zhang , Junping Zhang

Reinforcement learning (RL) has become a foundational approach for enabling intelligent robotic behavior in dynamic and uncertain environments. This work presents an in-depth review of RL principles, advanced deep reinforcement learning…

机器人学 · 计算机科学 2026-03-17 Kumater Ter , Abolanle Adetifa , Daniel Udekwe

Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration…

机器学习 · 计算机科学 2019-06-17 Pranav Shyam , Wojciech Jaśkowski , Faustino Gomez

Approximate Computing (AxC) techniques have become increasingly popular in trading off accuracy for performance gains in various applications. Selecting the best AxC techniques for a given application is challenging. Among proposed…

硬件体系结构 · 计算机科学 2024-01-01 Sepide Saeedi , Alessandro Savino , Stefano Di Carlo

In this work, we propose a deep reinforcement learning (DRL) based reactive planner to solve large-scale Lidar-based autonomous robot exploration problems in 2D action space. Our DRL-based planner allows the agent to reactively plan its…

机器人学 · 计算机科学 2024-03-19 Yuhong Cao , Rui Zhao , Yizhuo Wang , Bairan Xiang , Guillaume Sartoretti

The process of discovery requires active exploration -- the act of collecting new and informative data. However, efficient autonomous exploration remains a major unsolved problem. The dominant paradigm addresses this challenge by using…

机器学习 · 计算机科学 2026-05-14 Zakaria Mhammedi , James Cohan

The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent…

机器学习 · 计算机科学 2025-04-29 Amogh Joshi , Adarsh Kumar Kosta , Kaushik Roy

Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. To alleviate this issue, we propose to exploit the symmetries…

机器人学 · 计算机科学 2020-08-27 Yijiong Lin , Jiancong Huang , Matthieu Zimmer , Yisheng Guan , Juan Rojas , Paul Weng

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck…

机器学习 · 计算机科学 2019-06-11 Deepak Pathak , Dhiraj Gandhi , Abhinav Gupta

The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction…

机器人学 · 计算机科学 2022-04-29 Cristian C. Beltran-Hernandez , Damien Petit , Ixchel G. Ramirez-Alpizar , Kensuke Harada

We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov…

机器学习 · 计算机科学 2022-12-21 Piyush Gupta , Vaibhav Srivastava

Learning to manipulate objects efficiently, particularly those involving sustained contact (e.g., pushing, sliding) and articulated parts (e.g., drawers, doors), presents significant challenges. Traditional methods, such as robot-centric…

机器人学 · 计算机科学 2025-03-18 Shijie Fang , Wenchang Gao , Shivam Goel , Christopher Thierauf , Matthias Scheutz , Jivko Sinapov

Reinforcement Learning (RL) is increasingly applied to large-scale decision-making problems like logistics, scheduling, and recommender systems, but existing algorithms struggle with the curse of dimensionality in such large discrete action…

机器学习 · 计算机科学 2026-05-12 Heiko Hoppe , Fabian Akkerman , Wouter van Heeswijk , Maximilian Schiffer

Deep Reinforcement Learning (DRL) is widely used in task-oriented dialogue systems to optimize dialogue policy, but it struggles to balance exploration and exploitation due to the high dimensionality of state and action spaces. This…

计算与语言 · 计算机科学 2025-06-06 Yangyang Zhao , Ben Niu , Libo Qin , Shihan Wang

Radioguided surgery, such as sentinel lymph node biopsy, relies on the precise localization of radioactive targets by non-imaging gamma/beta detectors. Manual radioactive target detection based on visual display or audible indication of…

机器人学 · 计算机科学 2025-03-12 Hanyi Zhang , Kaizhong Deng , Zhaoyang Jacopo Hu , Baoru Huang , Daniel S. Elson

Effective and intelligent exploration has been an unresolved problem for reinforcement learning. Most contemporary reinforcement learning relies on simple heuristic strategies such as $\epsilon$-greedy exploration or adding Gaussian noise…

机器学习 · 计算机科学 2025-12-19 Muhammad Usama , Dong Eui Chang

Deep Reinforcement Learning has been successfully applied to learn robotic control. However, the corresponding algorithms struggle when applied to problems where the agent is only rewarded after achieving a complex task. In this context,…

机器人学 · 计算机科学 2023-04-18 Alexandre Chenu , Olivier Serris , Olivier Sigaud , Nicolas Perrin-Gilbert

Reinforcement learning (RL) and Deep Reinforcement Learning (DRL), in particular, have the potential to disrupt and are already changing the way we interact with the world. One of the key indicators of their applicability is their ability…

机器学习 · 计算机科学 2024-08-20 Nikolai Rozanov

Reinforcement learning (RL) suffers from low sample efficiency, particularly in high-dimensional continuous state-action spaces of complex robotic manipulation tasks. RL performance can improve by leveraging prior knowledge, even when…

机器人学 · 计算机科学 2025-09-23 Amir M. Soufi Enayati , Zengjie Zhang , Kashish Gupta , Homayoun Najjaran