中文
相关论文

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

200 篇论文

Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in…

人工智能 · 计算机科学 2019-11-18 Yijiong Lin , Jiancong Huang , Matthieu Zimmer , Juan Rojas , Paul Weng

Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires…

人工智能 · 计算机科学 2021-11-15 Jin Zhang , Jianhao Wang , Hao Hu , Tong Chen , Yingfeng Chen , Changjie Fan , Chongjie Zhang

The use of robotics in controlled environments has flourished over the last several decades and training robots to perform tasks using control strategies developed from dynamical models of their hardware have proven very effective. However,…

机器人学 · 计算机科学 2019-07-16 Zach Dwiel , Madhavun Candadai , Mariano Phielipp

Resource-constrained robots often suffer from energy inefficiencies, underutilized computational abilities due to inadequate task allocation, and a lack of robustness in dynamic environments, all of which strongly affect their performance.…

机器人学 · 计算机科学 2023-10-02 Dipam Patel , Phu Pham , Kshitij Tiwari , Aniket Bera

Mechanical search (MS) in cluttered environments remains a significant challenge for autonomous manipulators, requiring long-horizon planning and robust state estimation under occlusions and partial observability. In this work, we introduce…

机器人学 · 计算机科学 2025-06-17 Yiting Zhang , Shichen Li , Elena Shrestha

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able…

机器学习 · 计算机科学 2022-09-28 Desik Rengarajan , Sapana Chaudhary , Jaewon Kim , Dileep Kalathil , Srinivas Shakkottai

Safety is a crucial property of every robotic platform: any control policy should always comply with actuator limits and avoid collisions with the environment and humans. In reinforcement learning, safety is even more fundamental for…

机器人学 · 计算机科学 2023-03-02 Puze Liu , Kuo Zhang , Davide Tateo , Snehal Jauhri , Zhiyuan Hu , Jan Peters , Georgia Chalvatzaki

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models…

机器学习 · 计算机科学 2019-12-03 Mikael Henaff

Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have shown the effectiveness…

机器学习 · 计算机科学 2023-05-19 Shanchuan Wan , Yujin Tang , Yingtao Tian , Tomoyuki Kaneko

Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the…

机器人学 · 计算机科学 2021-08-09 Abdalkarim Mohtasib , Gerhard Neumann , Heriberto Cuayahuitl

Reinforcement Learning (RL) is a machine learning framework for artificially intelligent systems to solve a variety of complex problems. Recent years has seen a surge of successes solving challenging games and smaller domain problems,…

机器人学 · 计算机科学 2020-01-28 Florian Richter , Ryan K. Orosco , Michael C. Yip

Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes…

机器人学 · 计算机科学 2023-11-14 Luca Lach , Francesco Ferro , Robert Haschke

Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…

机器学习 · 计算机科学 2021-11-12 Ozsel Kilinc , Giovanni Montana

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games…

机器人学 · 计算机科学 2021-02-08 Julian Ibarz , Jie Tan , Chelsea Finn , Mrinal Kalakrishnan , Peter Pastor , Sergey Levine

This paper addresses the problem of designing control policies for agents with unknown stochastic dynamics and control objectives specified using Linear Temporal Logic (LTL). Recent Deep Reinforcement Learning (DRL) algorithms have aimed to…

机器人学 · 计算机科学 2025-04-23 Jun Wang , Hosein Hasanbeig , Kaiyuan Tan , Zihe Sun , Yiannis Kantaros

In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be…

机器学习 · 计算机科学 2019-11-26 Mingxuan Jing , Xiaojian Ma , Wenbing Huang , Fuchun Sun , Chao Yang , Bin Fang , Huaping Liu

In this paper we address the challenge of exploration in deep reinforcement learning for robotic manipulation tasks. In sparse goal settings, an agent does not receive any positive feedback until randomly achieving the goal, which becomes…

机器人学 · 计算机科学 2021-02-23 Nikola Vulin , Sammy Christen , Stefan Stevsic , Otmar Hilliges

Reinforcement learning (RL) is currently a popular research topic in control engineering and has the potential to make its way to industrial and commercial applications. Corresponding RL controllers are trained in direct interaction with…

机器学习 · 计算机科学 2021-10-20 Maximilian Schenke , Oliver Wallscheid

We present a novel technique called Dynamic Experience Replay (DER) that allows Reinforcement Learning (RL) algorithms to use experience replay samples not only from human demonstrations but also successful transitions generated by RL…

人工智能 · 计算机科学 2020-10-19 Jieliang Luo , Hui Li

Reinforcement learning (RL) excels in various applications but struggles in dynamic environments where the underlying Markov decision process evolves. Continual reinforcement learning (CRL) enables RL agents to continually learn and adapt…

机器学习 · 计算机科学 2025-12-23 Xue Yang , Michael Schukat , Junlin Lu , Patrick Mannion , Karl Mason , Enda Howley