Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Published in arXiv, 2025
Recommended citation: Tiofack, F. N., Le Hellard, T., Schramm, F., Perrin-Gilbert, N., & Carpentier, J. (2025). "Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning." arXiv preprint arXiv:2512.03973. https://arxiv.org/abs/2512.03973
Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their regularization components. We introduce Guided Flow Policy (GFP), which couples a multi-step flow-matching policy with a distilled one-step actor. The actor directs the flow policy through weighted behavior cloning to focus on cloning high-value actions from the dataset rather than indiscriminately imitating all state-action pairs. In turn, the flow policy constrains the actor to remain aligned with the dataset’s best transitions while maximizing the critic. This mutual guidance enables GFP to achieve state-of-the-art performance across 144 state and pixel-based tasks from the OGBench, Minari, and D4RL benchmarks, with substantial gains on suboptimal datasets and challenging tasks.