Research map / Multi-agent systems and games / Human-AI and goal-conditioned
A Scalable Framework to Choose Sellers in E-Marketplaces Using POMDPs
Athirai Irissappane, Frans A. Oliehoek, Jie Zhang
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 |
|---|---|---|---|
| use FF approximate belief update instead of exact belief update (ablation) | MOPE · e-marketplace | value | Hurt |
| use H3 hierarchy instead of H1 and H2 (ablation) | MOPE with majority voting · e-marketplace | error and value | Improved |
| increase subproblems per agent (SPA) from 4 to 8, and reduce to 2 (ablation) | H3 majority voting · e-marketplace | error and value | Improved |
| increase agents per subproblem (APS) from 5 to 6, 7 or 8 (ablation) | H3S8 · e-marketplace | value | Improved |
| increase APS from 7 to 8 (ablation) | H3S8 · e-marketplace | value | Hurt |
| use H3S8A7 instead of SALE POMDP at 100 agents | MOPE · e-marketplace, 100 agents | value: 65 -> 72 | Improved |
| use H3S8 instead of Max-Q and POMCP | MOPE · e-marketplace | error and value | Improved |
| increase number of agents for POMCP | POMCP · e-marketplace | error: 0.60 -> 0.90 | Hurt |
| use SALE POMDP instead of H3 when it can be solved | H3 · e-marketplace up to 10 agents | value | Mixed |
| use MOPE H3S4 instead of SRP for 5 neighbors | SRP model · WSN | policy time (s): 736s -> 73s | Improved |
| use MOPE H3S4 instead of SRP for 3-5 neighbors | SRP model · WSN | value | Hurt |
| scale MOPE H3S4 to 10-40 neighbors where SRP cannot solve | SRP model · WSN | value | Improved |
Closest papers by meaning
- HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems (AAAI 2026 · similarity 0.82)
- Factored Online Planning in Many-Agent POMDPs (AAAI 2024 · similarity 0.82)
- Strategic Recommendation: Revenue Optimal Matching for Online Platforms (Student Abstract) (AAAI 2024 · similarity 0.82)
- A Parametric Contextual Online Learning Theory of Brokerage (ICML 2025 · similarity 0.81)
- Mechanism Design via the Interim Relaxation (NeurIPS 2025 · similarity 0.81)
- Maximizing the Success Probability of Policy Allocations in Online Systems (AAAI 2024 · similarity 0.81)
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.
