Research map / Learning theory and algorithms / Submodular and game algorithms
Solving Partially Observable Stochastic Games with Public Observations
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 |
|---|---|---|---|
| increase attack time from t=3 to t=4 | PO-POSG algorithm · Patrolling | instances solved in under 20 minutes: 97 -> 82 | Hurt |
| skip Lipschitz envelope computation | PO-POSG algorithm · Patrolling | convergence | No clear effect |
| move from Patrolling to Lasertag domain | PO-POSG algorithm · Lasertag 4x4 | instances terminated in 5h: 16 of 20 not terminated | Hurt |
| reduce grid from 4x4 to 3x3 | PO-POSG algorithm · Lasertag | solve time: less than 8 seconds | Helped |
| larger patrolling graph (11 to 13 vertices) | PO-POSG algorithm · Patrolling t=4 | solve time (s): 307s -> 11004s | Hurt |
| pruning of alpha-beta vectors | PO-POSG algorithm · Patrolling 13-vertex | vectors retained: 50404 -> 22126 pruned | Helped |
| modify epsilon between iterations (eps_imm) | PO-POSG algorithm · all | trial length | Mixed |
| switch from Patrolling to Lasertag | PO-POSG algorithm · pruning cost | runtime share of pruning: 5% -> 22% | Hurt |
Closest papers by meaning
- Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees (AAAI 2026 · similarity 0.92)
- \(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs (NeurIPS 2025 · similarity 0.91)
- Learning Discrete-Time Major-Minor Mean Field Games (AAAI 2024 · similarity 0.85)
- Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics (NeurIPS 2026 · similarity 0.85)
- Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach (ICML 2024 · similarity 0.85)
- Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation (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.