Research map / Learning theory and algorithms / Submodular and game algorithms
Subgame solving without common knowledge
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 |
|---|---|---|---|
| Apply 1-KLSS at every infoset | Blueprint · 2x2 Abrupt Dark Hex | exploitability: .0683 -> .0625 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · 4-card Goofspiel, random order | exploitability: .171 -> .077 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · 4-card Goofspiel, increasing order | exploitability: .17 -> .0 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · Kuhn poker | exploitability: .0124 -> .0015 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · Kuhn poker (ε-bet) | exploitability: .0035 -> .0 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · 3-rank limit Leduc poker | exploitability: .0207 -> .0191 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · 3-rank limit Leduc poker (ε-fold) | exploitability: .0065 -> .0057 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · 3-rank limit Leduc poker (ε-bet) | exploitability: .0097 -> .0096 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · Liar's Dice, 5-sided die | exploitability: .181 -> .125 | Helped |
| Apply 1-KLSS at every infoset | Blueprint · 100-Matching pennies | exploitability: .0013 -> .0098 | Hurt |
| Use depth-limited 1-KLSS with a Stockfish-based value function | Dark chess agent · Dark chess, 100-game match against baseline agent | score: 59.5--40.5 | Helped |
| Use depth-limited 1-KLSS with a Stockfish-based value function | Dark chess agent · Dark chess, 10 games against FIDE Master Luis Chan | match score: 9--1 | Hurt |
Closest papers by meaning
- Safe and Nested Subgame Solving for Imperfect-Information Games (NeurIPS 2017 · similarity 0.93)
- Safe and Robust Subgame Exploitation in Imperfect Information Games (ICML 2024 · similarity 0.89)
- Opponent-Model Search in Games with Incomplete Information (AAAI 2024 · similarity 0.88)
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 2025 · similarity 0.86)
- The Update-Equivalence Framework for Decision-Time Planning (ICLR 2024 · similarity 0.86)
- Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions (NeurIPS 2024 · similarity 0.86)
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.