AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Behavior Regularization with Flow Latent Policy for Offline Reinforcement Learning

Yulong Xia, Fuchun Sun

AAAI 2026 · Reinforcement learning › Offline RL · approach: Behavior regularization for offline RL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add best-of-N sampling (N=4) (ablation)FLP · OGBench humanoid-medium, cube-doublesuccess rate (%)Improved
set KL coefficient alpha to 0.1 or 0.3 instead of moderate values (ablation)FLP · OGBench representative taskssuccess rate (%)Hurt
increase best-of-N samples from 4 to 8 or 16 (ablation)FLP · OGBench representative taskssuccess rate (%)No clear effect
latent-space Gaussian policy on frozen flow instead of one-step distilled flow policyFQL · OGBench cube-double (offline)success rate (%): 29 -> 69Improved
latent-space Gaussian policy on frozen flow instead of one-step distilled flow policyFQL · OGBench humanoid-m (offline)success rate (%): 58 -> 72Improved
latent-space Gaussian policy on frozen flow instead of one-step distilled flow policyFQL · OGBench antmaze-large (offline)success rate (%): 79 -> 75Hurt
latent-space Gaussian policy on frozen flow instead of one-step distilled flow policyFQL · OGBench cube-single (offline)success rate (%): 96 -> 93No clear effect
online fine-tuning with frozen flow, FLP vs FQLFLP · OGBench puzzle-4x4 (offline-to-online)success rate (%): 11 -> 99Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy