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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| warm-start progress-measure lifting after new data instead of re-solving game with symbolic fixpoint solver | data-driven game abstraction synthesis · 2D robot case study, 5 room updates | update runtime (s): 173.37 -> 18.69 (room 1) | Improved |
| incremental lifting for locally updated game graph | incremental game solving · 1x1 region update across graph sizes | update runtime | Improved |
| incremental lifting vs fixpoint recomputation on result quality | incremental game solving · 2D robot case study | winning region | No clear effect |
| add new data samples to the learned abstraction | abstract fair Buchi game · 2D robot case study | winning region size | Improved |
| smaller progress-measure range for abstract game DAG structure | cofair coBuchi progress measure · abstract game | PM range: reduced to [0, |S| + |B|] | Improved |
Closest papers by meaning
- State-Action Selection in General Stochastic Games under Regularized Policy Gradient Methods (NeurIPS 2026 · similarity 0.88)
- Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence (ICML 2021 · similarity 0.87)
- Approximate State Abstraction for Markov Games (AAAI 2025 · similarity 0.86)
- RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning (ICML 2024 · similarity 0.86)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.86)
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence (ICLR 2025 · similarity 0.85)
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.
