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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Offline Reinforcement Learning | OGBench | AntMaze Giant Navigate41 | 78 | |
| Offline Reinforcement Learning | D4RL AntMaze | Medium Diverse Success Rate71.8 | 27 | |
| Reinforcement Learning | D4RL Antmaze v2 (offline-to-online) | Score (umaze-default)96.3 | 5 |