Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy

About

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains challenging, as naive gradient-based optimization requires backpropagating through numerical solvers and often leads to instability. Existing approaches typically address this issue by restricting the expressive capacity of flow-based policies, resulting in a trade-off between optimization stability and representational flexibility. To resolve this, we introduce Q-Flow, a framework that leverages the deterministic nature of flow dynamics to explicitly propagate terminal trajectory value to intermediate latent states along the policy-induced flow. This formulation enables stable policy optimization using intermediate value gradients without unrolling the numerical solver, effectively bridging the gap between stability and expressivity. We evaluate Q-Flow in the offline learning setting on the challenging OGBench suite, where it consistently outperforms state-of-the-art baselines by an average of 10.6 percentage points, while also enabling stable online adaptation within the same framework.

JaeHyeok Doo, Byeongguk Jeon, Seonghyeon Ye, Kimin Lee, Minjoon Seo• 2026

Related benchmarks

TaskDatasetResultRank
Offline Reinforcement LearningOGBench
AntMaze Giant Navigate41
78
Offline Reinforcement LearningD4RL AntMaze
Medium Diverse Success Rate71.8
27
Reinforcement LearningD4RL Antmaze v2 (offline-to-online)
Score (umaze-default)96.3
5
Showing 3 of 3 rows

Other info

Follow for update