AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization

Min Wang, Xin Li, Mingzhong Wang, Hasnaa Bennis

AAAI 2026 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 1 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 FLORA (flow task inference plus adaptive correction) over best baselinesFLORA · Meta-World ML1 Plate-Slide-Backsuccess rate (%): 61.75 -> 73.25 (vs FOCAL)Improved
FLORA versus IDAQ on suboptimal-data task PushFLORA · Meta-World ML1 Pushsuccess rate (%): 18.00 -> 50.07Improved
remove ACO and FTI modules (ablation)FLORA · Meta-World / MuJoCo ablationreturn / successImproved
use decomposed Q instead of vanilla or distributional Q (ablation)FLORA · Point-Robot-WindreturnImproved
use distributional Q instead of vanilla Q (ablation)FLORA backbone · Point-Robot-WindreturnImproved
Q-value decomposition without overgeneralization correctionoffline meta-RL policy · Drawer-Close vs Door-Close (Figure 1)policy performanceMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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