中文
相关论文

相关论文: Multi-Fidelity Hybrid Reinforcement Learning via I…

200 篇论文

Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using…

系统与控制 · 电气工程与系统科学 2020-03-03 Yao Mu , Shengbo Eben Li , Chang Liu , Qi Sun , Bingbing Nie , Bo Cheng , Baiyu Peng

Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…

计算机视觉与模式识别 · 计算机科学 2023-01-18 Yaoyao Liu , Bernt Schiele , Qianru Sun

Various methods for solving the inverse reinforcement learning (IRL) problem have been developed independently in machine learning and economics. In particular, the method of Maximum Causal Entropy IRL is based on the perspective of entropy…

机器学习 · 计算机科学 2021-03-05 Navyata Sanghvi , Shinnosuke Usami , Mohit Sharma , Joachim Groeger , Kris Kitani

Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding…

机器学习 · 计算机科学 2021-01-01 Tianwei Ni , Harshit Sikchi , Yufei Wang , Tejus Gupta , Lisa Lee , Benjamin Eysenbach

In various control task domains, existing controllers provide a baseline level of performance that -- though possibly suboptimal -- should be maintained. Reinforcement learning (RL) algorithms that rely on extensive exploration of the state…

机器学习 · 计算机科学 2022-09-21 Sheelabhadra Dey , Sumedh Pendurkar , Guni Sharon , Josiah P. Hanna

Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while…

机器学习 · 计算机科学 2023-07-25 Jiachen Li , Edwin Zhang , Ming Yin , Qinxun Bai , Yu-Xiang Wang , William Yang Wang

The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL,…

机器学习 · 计算机科学 2024-11-05 Miao Lu , Han Zhong , Tong Zhang , Jose Blanchet

Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL leverages extensive pre-collected data to learn policies, but…

机器学习 · 计算机科学 2026-03-10 Xuefeng Liu , Hung T. C. Le , Siyu Chen , Rick Stevens , Zhuoran Yang , Matthew R. Walter , Yuxin Chen

Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human…

机器学习 · 计算机科学 2023-06-01 Philip J. Ball , Laura Smith , Ilya Kostrikov , Sergey Levine

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

机器学习 · 计算机科学 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma

In robotics and multi-agent systems, fleets of autonomous agents often operate in subtly different environments while pursuing a common high-level objective. Directly pooling their data to learn a shared reward function is typically…

机器学习 · 计算机科学 2026-01-05 David Millard , Ali Baheri

Reinforcement learning (RL) has been extensively employed in a wide range of decision-making problems, such as games and robotics. Recently, diffusion policies have shown strong potential in modeling multi-modal behaviors, enabling more…

机器学习 · 计算机科学 2026-03-06 Ben Liu , Shunpeng Yang , Hua Chen

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

机器学习 · 计算机科学 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offline datasets for pretraining and online interactions for fine-tuning. However, its empirical behavior is highly inconsistent: design…

机器学习 · 计算机科学 2026-02-03 Lu Li , Tianwei Ni , Yihao Sun , Pierre-Luc Bacon

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

机器学习 · 计算机科学 2022-08-09 Taisuke Kobayashi , Kenta Yoshizawa

The integration of distributed energy resources (DER) has escalated the challenge of voltage magnitude regulation in distribution networks. Traditional model-based approaches, which rely on complex sequential mathematical formulations,…

系统与控制 · 电气工程与系统科学 2024-11-05 Shengren Hou , Peter Palensky , Pedro P. Vergara

Autonomous driving has achieved significant progress in recent years, but autonomous cars are still unable to tackle high-risk situations where a potential accident is likely. In such near-accident scenarios, even a minor change in the…

机器学习 · 计算机科学 2020-07-02 Zhangjie Cao , Erdem Bıyık , Woodrow Z. Wang , Allan Raventos , Adrien Gaidon , Guy Rosman , Dorsa Sadigh

The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \emph{$f$-Divergence Reinforcement…

机器学习 · 计算机科学 2021-12-15 Chen Gong , Qiang He , Yunpeng Bai , Zhou Yang , Xiaoyu Chen , Xinwen Hou , Xianjie Zhang , Yu Liu , Guoliang Fan

Informative path planning (IPP) is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment while adhering to resource constraints. Reinforcement learning (RL) has been shown to be…

机器人学 · 计算机科学 2024-09-26 Srikar Babu Gadipudi , Srujan Deolasee , Siva Kailas , Wenhao Luo , Katia Sycara , Woojun Kim

Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly susceptible to the error in cumulative cost estimation since…

机器学习 · 计算机科学 2024-04-16 Zifan Wu , Bo Tang , Qian Lin , Chao Yu , Shangqin Mao , Qianlong Xie , Xingxing Wang , Dong Wang