← Back to all news
arXiv Machine Learning By Zhancun Mu, Chi Zhang

DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction

Read the original on arXiv Machine Learning →

DeFlow is a decoupled offline reinforcement learning framework that uses flow matching to accurately model complex behavior manifolds. Instead of backpropagating through ODE solvers, it learns a lightweight refinement module within a data‑derived trust region of the flow manifold, preserving iterative expressivity while avoiding solver differentiation. The approach eliminates the need for balancing loss terms and achieves superior performance on the OGBench benchmark, also enabling efficient offline‑to‑online adaptation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 4

Multi-step Proximal Policy Improvement in Offline Reinforcement Learning

The paper introduces Multi-step Proximal Policy Improvement (MPI), a method that refines offline reinforcement learning policies through sequential re-centered proximal steps. By viewing policies as a probability manifold, MPI interprets a wide range of offline actor objectives as a single proximal policy improvement step and extends this to multiple steps for controlled policy improvement beyond the behavior distribution. Experiments on D4RL benchmarks demonstrate that a few MPI refinements enhance strong offline baselines such as TD3+BC, ReBRAC, and IQL, while diagnostics clarify the benefits of re-centered refinement over fixed-objective scheduling and highlight critic error limitations.

By Soohyun Choi, Seonvin Cho, Songnam Hong
reinforcement-learningbenchmarks
More like this →
Hugging Face Trending Papers
Sep 3

Multi-step Proximal Policy Improvement in Offline Reinforcement Learning

The paper introduces Multi-step Proximal Policy Improvement (MPI), a method that refines offline reinforcement learning policies through sequential re-centered proximal steps. By modeling policies as a probability manifold, MPI interprets a wide range of offline actor objectives as a single proximal policy improvement step and extends this to multiple steps for controlled policy improvement beyond the behavior distribution. Experiments on D4RL benchmarks demonstrate that a few MPI refinements enhance strong offline baselines such as TD3+BC, ReBRAC, and IQL across many tasks, while diagnostics clarify the benefits of re-centered refinement over fixed-objective scheduling and highlight critic error limitations.

reinforcement-learningbenchmarks
More like this →