3 papers
cs.LG2026
Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning
Zhiqiang Dong, Teng Pang, Rongjian Xu +1
Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. De…
cs.LG2026
Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation
Rongjian Xu, Teng Pang, Zhiqiang Dong +1
Graph-structured data jointly contain discrete topology and continuous geometry, which poses fundamental challenges for generative modeling due to heterogeneous distributions, inco…
cs.LG2026
Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning
Teng Pang, Zhiqiang Dong, Yan Zhang +3
Offline multi-agent reinforcement learning (MARL) aims to learn the optimal joint policy from pre-collected datasets, requiring a trade-off between maximizing global returns and mi…