Research map / Learning theory and algorithms / Submodular and game algorithms
On Markov Games Played by Bayesian and Boundedly-Rational Players
Muthukumaran Chandrasekaran, Yingke Chen, Prashant Doshi
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 |
|---|---|---|---|
| add type equivalence, H=3, 64 types (ablation) | BMG CSP · 2MABC | time (s): 1335.6 -> 27.2 | Improved |
| add type equivalence, H=4, 64 types (ablation) | BMG CSP · 2MABC | time (s): 1481.1 -> 311.2 | Improved |
| add type equivalence, H=5, 64 types (ablation) | BMG CSP · 2MABC | time (s): >1 day -> 3161.7 | Improved |
| add type equivalence, H=3, 16 types (ablation) | BMG CSP · 2MABC | time (s): 0.07 -> 0.11 | Hurt |
| add type equivalence, H=4, 36 types (ablation) | BMG CSP · 2MABC | time (s): 42.6 -> 14.3 | Improved |
| add type equivalence, H=5, 36 types (ablation) | BMG CSP · 2MABC | time (s): 31.2 -> 26.7 | Mixed |
| add type equivalence, H=4, 16 types (ablation) | BMG CSP · 2MABC | time (s): 1.01 -> 0.96 | No clear effect |
| add type equivalence, H=3, 36 types (ablation) | BMG CSP · 2MABC | time (s): 0.8 -> 0.54 | No clear effect |
| coarser discretization tau on 3x3 Foraging | BMG CSP · 3x3 Foraging H=2 | run time | Improved |
| increase horizon to 5 in 5MABC | BMG CSP · 5MABC eps=0.1 | run time | Hurt |
| compute exact instead of approximate equilibria | BMG CSP · 5MABC | run time | Hurt |
| larger eps (coarser approximation) | BMG CSP · 2MABC/3MABC | run time | Improved |
Closest papers by meaning
- Playing Markov Games Without Observing Payoffs (NeurIPS 2026 · similarity 0.87)
- Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach (ICML 2024 · similarity 0.87)
- State-Constrained Zero-Sum Differential Games with One-Sided Information (ICML 2024 · similarity 0.86)
- Safe Exploitative Play with Untrusted Type Beliefs (NeurIPS 2024 · similarity 0.86)
- Anytime-Constrained Equilibria in Polynomial Time (ICML 2025 · similarity 0.85)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (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.
