Trajectory alignment via diffusion models in cross-domain offline reinforcement learning

Yujia ZHANG; Lin LI; Jianguo WU; Ting GUO; Wei WEI; Jiye LIANG

doi:10.1007/s11704-026-52191-9

Front. Comput. Sci. ›› 2027, Vol. 21 ›› Issue (7) :2107345 DOI: 10.1007/s11704-026-52191-9

Artificial Intelligence

LETTER

Trajectory alignment via diffusion models in cross-domain offline reinforcement learning

Author information +

History +

PDF (254KB)

Cite this article

Download citation ▾

Yujia ZHANG, Lin LI, Jianguo WU, Ting GUO, Wei WEI, Jiye LIANG. Trajectory alignment via diffusion models in cross-domain offline reinforcement learning. Front. Comput. Sci., 2027, 21 (7) : 2107345 DOI:10.1007/s11704-026-52191-9

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Zhang Y, Li L, Wei W, Wu J, Ma Y, Liang J. Efficient offline reinforcement learning via peer-influenced constraint. In: Proceedings of the 14th International Conference on Learning Representations. 2026

[2]	Liu J, Zhang H, Wang D. DARA: dynamics-aware reward augmentation in offline reinforcement learning. In: Proceedings of the 10th International Conference on Learning Representations. 2022

[3]	Xue Z, Cai Q, Liu S, Zheng D, Jiang P, Gai K, An B. State regularized policy optimization on data with dynamics shift. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. 2023, 1427

[4]	Lyu J, Yan M, Qiao Z, Liu R, Ma X, Ye D, Yang J, Lu Z, Li X. Cross-domain offline policy adaptation with optimal transport and dataset constraint. In: Proceedings of the 13th International Conference on Learning Representations. 2025

[5]	Ajay A, Du Y, Gupta A, Tenenbaum J B, Jaakkola T S, Agrawal P. Is conditional generative modeling all you need for decision making? In: Proceedings of the 11th International Conference on Learning Representations. 2023

[6]	Lyu J, Xu K, Xu J, Yan M, Yang J, Zhang Z, Bai C, Lu Z, Li X. ODRL: a benchmark for off-dynamics reinforcement learning. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 1912

[7]	Kostrikov I, Nair A, Levine S. Offline reinforcement learning with implicit Q-learning. In: Proceedings of the 10th International Conference on Learning Representations. 2022

[8]	Liu J, Zhang Z, Wei Z, Zhuang Z, Kang Y, Gai S, Wang D. Beyond OOD state actions: supported cross-domain offline reinforcement learning. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. 2024, 13945−13953

[9]	Wen X, Bai C, Xu K, Yu X, Zhang Y, Li X, Wang Z. Contrastive representation for data filtering in cross-domain offline reinforcement learning. In: Proceedings of the 41st International Conference on Machine Learning. 2024, 52720−52743

[10]	Bai C, Wang L, Hao J, Yang Z, Zhao B, Wang Z, Li X . Pessimistic value iteration for multi-task data sharing in offline reinforcement learning. Artificial Intelligence, 2024, 326: 104048