中文
相关论文

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

200 篇论文

Experimentation on real robots is demanding in terms of time and costs. For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and benchmark algorithms. However, insights gained in simulation…

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes…

机器学习 · 计算机科学 2025-02-12 Zelei Cheng , Jiahao Yu , Xinyu Xing

A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a reward function that makes the demonstrator appear near-optimal,…

机器学习 · 计算机科学 2019-07-10 Daniel S. Brown , Wonjoon Goo , Prabhat Nagarajan , Scott Niekum

Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to curent…

人工智能 · 计算机科学 2026-03-23 Wenjian Zhang , Kongcheng Zhang , Jiaxin Qi , Baisheng Lai , Jianqiang Huang

To increase autonomy in reinforcement learning, agents need to learn useful behaviours without reliance on manually designed reward functions. To that end, skill discovery methods have been used to learn the intrinsic options available to…

人工智能 · 计算机科学 2021-08-05 Even Klemsdal , Sverre Herland , Abdulmajid Murad

Deep reinforcement learning (DRL) has been proven its efficiency in capturing users' dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL…

信息检索 · 计算机科学 2022-09-20 Xiaocong Chen , Siyu Wang , Lina Yao , Lianyong Qi , Yong Li

Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement learning (RL) in…

机器学习 · 计算机科学 2022-12-08 Chao Li

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…

机器人学 · 计算机科学 2022-09-19 Zhenshan Bing , Alexander Koch , Xiangtong Yao , Kai Huang , Alois Knoll

This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning…

机器学习 · 统计学 2017-06-20 Nick Erickson , Qi Zhao

Teaching dexterity to multi-fingered robots has been a longstanding challenge in robotics. Most prominent work in this area focuses on learning controllers or policies that either operate on visual observations or state estimates derived…

机器人学 · 计算机科学 2023-03-22 Irmak Guzey , Ben Evans , Soumith Chintala , Lerrel Pinto

Dexterous manipulation is a critical aspect of human capability, enabling interaction with a wide variety of objects. Recent advancements in learning from human demonstrations and teleoperation have enabled progress for robots in such…

机器人学 · 计算机科学 2026-01-14 Shuqi Zhao , Xinghao Zhu , Yuxin Chen , Chenran Li , Lichen Xie , Xiang Zhang , Mingyu Ding , Masayoshi Tomizuka

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

最优化与控制 · 数学 2024-01-04 Daokuan Zhu , Tianqi Xu , Jie Lu

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

Purpose: This paper focuses on an automated analysis of surgical motion profiles for objective skill assessment and task recognition in robot-assisted surgery. Existing techniques heavily rely on conventional statistic measures or shallow…

计算机视觉与模式识别 · 计算机科学 2019-01-09 Ziheng Wang , Ann Majewicz Fey

Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that…

机器学习 · 计算机科学 2026-05-20 Luca Vignola , Bruce D. Lee , Manish Prajapat , Manuel Wendl , Melanie Zeilinger , Andreas Krause , Yarden As

Dexterous manipulation with anthropomorphic robot hands remains a challenging problem in robotics because of the high-dimensional state and action spaces and complex contacts. Nevertheless, skillful closed-loop manipulation is required to…

机器人学 · 计算机科学 2022-12-06 Malte Mosbach , Kara Moraw , Sven Behnke

Traditional control methods effectively manage robot operations using models like motion equations but face challenges with issues of contact and friction, leading to unstable and imprecise controllers that often require manual tweaking.…

机器人学 · 计算机科学 2024-09-20 Bahador Beigomi , Zheng H. Zhu

Reinforcement learning (RL) is emerging as a powerful paradigm for enabling large language models (LLMs) to perform complex reasoning tasks. Recent advances indicate that integrating RL with retrieval-augmented generation (RAG) allows LLMs…

计算与语言 · 计算机科学 2025-08-13 Wentao Jiang , Xiang Feng , Zengmao Wang , Yong Luo , Pingbo Xu , Zhe Chen , Bo Du , Jing Zhang

In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode. Typical applications include robotic control with limited energy…

机器学习 · 计算机科学 2022-12-15 Zhihai Wang , Taoxing Pan , Qi Zhou , Jie Wang

Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable,…

机器学习 · 计算机科学 2021-03-22 Thomas D. Barrett , William R. Clements , Jakob N. Foerster , A. I. Lvovsky