Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning

arXiv:2604.08960v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as HIQL, long-horizon control in offline GCRL remains challenging due to the limited expressiveness of Gaussian policies and the inability of high-level policies to generate effective subgoals. To address these limitations, we propose the goal-conditioned mean flow policy, which introduces an average velocity field into hierarchical policy modeling for offline GCRL. Specifically, the mean flow policy captures complex target distributions for both high-level and low-level policies through a learned average velocity field, enabling efficient action generation via one-step sampling. Furthermore, considering the insufficiency of goal representation, we introduce a LeJEPA loss that repels goal representation embeddings during training, thereby encouraging more discriminative representations and improving generalization. Experimental results show that our method achieves strong performance across both state-based and pixel-based tasks in the OGBench benchmark.

Related

• Epistemic Robust Offline Reinforcement Learning
• Tensor-Efficient High-Dimensional Q-learning
• DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning
• Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
• Adaptive Tuning of Parameterized Traffic Controllers via Multi-Agent Reinforcement Learning

Source: arXiv cs.LG | 2026-04-13