Research map / Multi-agent systems and games / Games and equilibria
Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing
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 |
|---|---|---|---|
| Use linear value representation (HSVI1) instead of PWLC with enumeration (HSVI2) or MILP (HSVI3) | HSVI variants for one-sided Dec-POMDPs · mabc, tiger, Grid3x3corners, Recycling, boxPushing, Mars | running time: mabc: 0.004 s vs 0.02 s (HSVI2) and 0.8 s (HSVI3) | Helped |
| Use PWLC representation with enumeration (HSVI2) instead of linear (HSVI1) | HSVI variants · Recycling, boxPushing, Grid3x3corners | number of iterations to converge: Recycling #it 83 (HSVI1(1)) vs 50 (HSVI2) | Helped |
| Use PWLC with enumeration (HSVI2) instead of MILP action selection (HSVI3) | HSVI2 vs HSVI3 · small and medium domains | running time | Helped |
| Increase history length m in HSVI1(m) from 1 to larger values (ablation) | HSVI1(m) on tiger · tiger | convergence (gap at s0): HSVI1(1) gap -0.139; HSVI1(7) gap 0.0 with lower bound 37.5 | Mixed |
| Use small history length m (1,2,6) in HSVI1(m) (ablation) | HSVI1(m) on tiger · tiger | bound consistency (lower above upper) | Hurt |
| Use linear HSVI1 with m=1 on Mars vs HSVI2/HSVI3 PWLC variants | HSVI1(1) · Mars | running time: 34.0906 s vs 13196.4 s (HSVI2) and 19045.7 s (HSVI3) | Helped |
| Use HSVI2 (PWLC enumeration) on Grid3x3corners with largest observation set | HSVI2 · Grid3x3corners | completion: out of memory | Hurt |
Closest papers by meaning
- Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach (ICML 2024 · similarity 0.88)
- Multi-Environment POMDPs with Finite-Horizon Objectives (NeurIPS 2026 · similarity 0.87)
- Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives (AAAI 2025 · similarity 0.86)
- Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach (AAAI 2025 · similarity 0.86)
- Belief-State Query Policies for User-Aligned POMDPs (NeurIPS 2024 · similarity 0.86)
- Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies (ICML 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.