AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Incremental Data-Driven Policy Synthesis via Game Abstractions

Irmak Sağlam, Mahdi Nazeri, Alessandro Abate, Sadegh Soudjani, Anne-Kathrin Schmuck

AAAI 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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
warm-start progress-measure lifting after new data instead of re-solving game with symbolic fixpoint solverdata-driven game abstraction synthesis · 2D robot case study, 5 room updatesupdate runtime (s): 173.37 -> 18.69 (room 1)Improved
incremental lifting for locally updated game graphincremental game solving · 1x1 region update across graph sizesupdate runtimeImproved
incremental lifting vs fixpoint recomputation on result qualityincremental game solving · 2D robot case studywinning regionNo clear effect
add new data samples to the learned abstractionabstract fair Buchi game · 2D robot case studywinning region sizeImproved
smaller progress-measure range for abstract game DAG structurecofair coBuchi progress measure · abstract gamePM range: reduced to [0, |S| + |B|]Improved

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