X Liu, Y Chen, H Li, B Li, D Zhao - arXiv preprint arXiv:2302.05614, 2023 - arxiv.org
Task-agnostic cross-domain pre-training shows great potential in image-based Reinforcement Learning (RL) but poses a big challenge. In this paper, we propose …
M Liu, Y Zhu, Y Chen, D Zhao - IEEE Transactions on Artificial …, 2024 - ieeexplore.ieee.org
Enhancing state representations can effectively mitigate the issue of low sample efficiency in reinforcement learning (RL) within high-dimensional input environments. Existing methods …
Z Gao, Y Mu, J Qu, M Hu, L Guo, P Luo, Y Lu - arXiv preprint arXiv …, 2024 - arxiv.org
Dual-arm robots offer enhanced versatility and efficiency over single-arm counterparts by enabling concurrent manipulation of multiple objects or cooperative execution of tasks using …
X Song, J Duan, W Wang, SE Li… - International …, 2023 - proceedings.mlr.press
Deep reinforcement learning (RL) is a powerful approach for solving optimal control problems. However, RL-trained policies often suffer from the action fluctuation problem …
Y Mu, Z Lan, C Chen, C Liu, P Luo… - 2023 IEEE 26th …, 2023 - ieeexplore.ieee.org
The multi-lane roundabout poses significant challenges for autonomous driving due to its complex road structure and traffic conditions. To address these challenges, this paper …
C Ouyang, Z Zhan, F Lv - World Electric Vehicle Journal, 2024 - mdpi.com
In recent years, the increasing production and sales of automobiles have led to a notable rise in congestion on urban road traffic systems, particularly at ramps and intersections with …
B Li, H Li, Y Zhu, D Zhao - IEEE Transactions on Cognitive and …, 2024 - ieeexplore.ieee.org
Agent-agnostic reinforcement learning aims to learn a universal control policy that can simultaneously control a set of robots with different morphologies. Recent studies have …
Q Wang, J Yang, Y Wang, X Jin, W Zeng… - arXiv preprint arXiv …, 2023 - arxiv.org
Training offline reinforcement learning (RL) models using visual inputs poses two significant challenges, ie, the overfitting problem in representation learning and the overestimation bias …