New!  CarDreamer:  A simulation platform for training and testing world-model based reinforcement learning algorithms for autonomous driving: https://github.com/ucd-dare/CarDreamer  

[1] S. Lin and J. Wan and T. Xu and Y. Liang and J. Zhang, “Model-Based Offline Meta-Reinforcement Learning with Regularization,” Proc. International Conference on Learning Representations (ICLR) 2022, p. 1-22.

[2] Sheng Yue and Guanbo Wang and Wei Shao and Zhaofeng Zhang and Sen Lin and Ju Ren and Junshan Zhang:
“CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning.” Proc. International Conference on Learning Representations (ICLR) 2023, p. 1-23. 

[3] Mehmet Dedeoglu,and Sen Lin and Zhaofeng Zhang and Junshan Zhang, “Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence,” IEEE Transactions on Neural Networks and Learning Systems, 2023.

[4] H. Wang S. Lin and J. Zhang, “Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap,” ICML 2023 (`Oral & poster’).  

[5] Jialin Wan and Sen Lin and Zhaofeng Zhang and Junshan Zhang and Tao Zhang, “Scheduling Real-time Wireless Traffic: A Network-aided Offline Reinforcement Learning Approach,” IEEE Internet of Things Journal. DOI: 10.1109/JIOT.2023.3304969.

[6] Ashvin Srinivasan, Mohsen Amidzadeh, Junshan Zhang, Olav Tirkkonen:
Adaptive Cache Policy Optimization Through Deep Reinforcement Learning in Dynamic Cellular Networks. Intell. Converged Networks 5(2): 81-99 (2024)

[7] Sheng Yue, Jiani Liu, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, Yaoxue Zhang:
How to Leverage Diverse Demonstrations in Offline Imitation Learning. ICML 2024

[8] Sheng Yue, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, Yaoxue Zhang:
OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning. ICML 2024

[9] Imran Adham, Hang Wang, Sen Lin, Junshan Zhang:
L-MBOP-E: Latent-Model Based Offline Planning with Extrinsic Policy Guided Exploration. MOST 2024: 178-185.