Research map / Learning theory and algorithms / Submodular and game algorithms
Refining Subgames in Large Imperfect Information Games
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| maximize subgame margin (max-margin gadget) instead of only feasibility (re-solving) | Nyx river subgame refinement · HUNL river subgames | subgame margin: 8.79 -> 101.49 | Helped |
| add exploitability-bounding constraints (re-solving) to unconstrained endgame solving | Nyx river subgame refinement · HUNL river subgames | subgame margin: −518.5 -> 8.79 | Helped |
Closest papers by meaning
- Safe and Nested Subgame Solving for Imperfect-Information Games (NeurIPS 2017 · similarity 0.92)
- History Filtering in Imperfect Information Games: Algorithms and Complexity (NeurIPS 2023 · similarity 0.91)
- Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach (ICML 2024 · similarity 0.86)
- Safe and Robust Subgame Exploitation in Imperfect Information Games (ICML 2024 · similarity 0.86)
- The Update-Equivalence Framework for Decision-Time Planning (ICLR 2024 · similarity 0.85)
- Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play (NeurIPS 2024 · 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.