English
Related papers

Related papers: Cross-Domain Policy Optimization via Bellman Consi…

200 papers

Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain by leveraging data collected from a source domain. Existing works typically assess the transferability of source-domain data by measuring…

Machine Learning · Computer Science 2026-05-22 Wei Liu , Ting Long

Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to…

Machine Learning · Computer Science 2026-03-23 Zhongjian Qiao , Rui Yang , Jiafei Lyu , Chenjia Bai , Xiu Li , Siyang Gao , Shuang Qiu

In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task…

Artificial Intelligence · Computer Science 2018-01-23 Girish Joshi , Girish Chowdhary

Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering…

Machine Learning · Computer Science 2024-11-22 Sergio A. Serrano , Jose Martinez-Carranza , L. Enrique Sucar

Cross-domain offline reinforcement learning (RL) seeks to enhance sample efficiency in offline RL by utilizing additional offline source datasets. A key challenge is to identify and utilize source samples that are most relevant to the…

Machine Learning · Computer Science 2025-10-28 Linh Le Pham Van , Minh Hoang Nguyen , Duc Kieu , Hung Le , Hung The Tran , Sunil Gupta

Training a robotic policy from scratch using deep reinforcement learning methods can be prohibitively expensive due to sample inefficiency. To address this challenge, transferring policies trained in the source domain to the target domain…

Robotics · Computer Science 2024-03-05 Ruiqi Zhu , Tianhong Dai , Oya Celiktutan

It remains a critical challenge to adapt policies across domains with mismatched dynamics in reinforcement learning (RL). In this paper, we study cross-domain offline RL, where an offline dataset from another similar source domain can be…

Machine Learning · Computer Science 2026-02-06 Mengbei Yan , Jiafei Lyu , Shengjie Sun , Zhongjian Qiao , Jingwen Yang , Zichuan Lin , Deheng Ye , Xiu Li

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset…

Machine Learning · Computer Science 2026-05-26 Zhongjian Qiao , Jiafei Lyu , Chenjia Bai , Peisong Wang , Siyang Gao , Shuang Qiu

Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that…

Machine Learning · Computer Science 2018-09-25 Yue Wang , Qi Meng , Wei Cheng , Yuting Liug , Zhi-Ming Ma , Tie-Yan Liu

Domain Randomization (DR) is commonly used for sim2real transfer of reinforcement learning (RL) policies in robotics. Most DR approaches require a simulator with a fixed set of tunable parameters from the start of the training, from which…

Cross-Domain Sequential Recommendation (CDSR) improves recommendation performance by utilizing information from multiple domains, which contrasts with Single-Domain Sequential Recommendation (SDSR) that relies on a historical interaction…

Information Retrieval · Computer Science 2024-07-25 Chung Park , Taesan Kim , Hyungjun Yoon , Junui Hong , Yelim Yu , Mincheol Cho , Minsung Choi , Jaegul Choo

Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised,…

Machine Learning · Computer Science 2026-02-12 Li-Min Chu , Kai-Siang Ma , Ming-Hong Chen , Ping-Chun Hsieh

In the recommendation systems, there are multiple business domains to meet the diverse interests and needs of users, and the click-through rate(CTR) of each domain can be quite different, which leads to the demand for CTR prediction…

Information Retrieval · Computer Science 2023-06-30 Wei Zhang , Pengye Zhang , Bo Zhang , Xingxing Wang , Dong Wang

Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused…

Machine Learning · Computer Science 2024-07-25 Hayato Watahiki , Ryo Iwase , Ryosuke Unno , Yoshimasa Tsuruoka

Cross-domain recommendation (CDR) is an important method to improve recommender system performance, especially when observations in target domains are sparse. However, most existing cross-domain recommendations fail to fully utilize the…

Information Retrieval · Computer Science 2024-01-23 Yuhao Luo , Shiwei Ma , Mingjun Nie , Changping Peng , Zhangang Lin , Jingping Shao , Qianfang Xu

Cross-domain reinforcement learning (RL) aims to learn transferable policies under dynamics shifts between source and target domains. A key challenge lies in the lack of target-domain environment interaction and reward supervision, which…

Machine Learning · Computer Science 2026-03-02 Hanping Zhang , Yuhong Guo

Deep Reinforcement Learning (DRL) emerges as a prime solution for Unmanned Aerial Vehicle (UAV) trajectory planning, offering proficiency in navigating high-dimensional spaces, adaptability to dynamic environments, and making sequential…

Signal Processing · Electrical Eng. & Systems 2024-05-17 Chenrui Sun , Gianluca Fontanesi , Swarna Bindu Chetty , Xuanyu Liang , Berk Canberk , Hamed Ahmadi

It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics adaptation settings where there exists dynamics mismatch…

Machine Learning · Computer Science 2024-05-27 Jiafei Lyu , Chenjia Bai , Jingwen Yang , Zongqing Lu , Xiu Li

Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. Existing approaches achieve this either by aligning the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Kai Li , Curtis Wigington , Chris Tensmeyer , Vlad I. Morariu , Handong Zhao , Varun Manjunatha , Nikolaos Barmpalios , Yun Fu

Domain randomization has emerged as a fundamental technique in reinforcement learning (RL) to facilitate the transfer of policies from simulation to real-world robotic applications. Many existing domain randomization approaches have been…

‹ Prev 1 2 3 10 Next ›