Research map / Reinforcement learning / MDPs and planning
Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs
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 |
|---|---|---|---|
| exploit anonymous influence via redundant representation (RR-ALP) instead of standard ALP | ALP for factored MMDPs · Disease control, 10 random 30-node graphs | ALP solution time: average relative runtime 0.16 of original | Helped |
| exploit anonymous influence in variable elimination (RR-VE vs VE) | variable elimination · Disease control, random graphs | VE time: average relative 0.25; graph 1: 6.2s -> 1.5s | Helped |
| use redundant representation instead of standard factor tables | ALP constraint set · Disease control, random graphs | constraint set size: average relative size 0.53 | Helped |
| RR-ALP on denser graph (out-degree up to 20) | RR-ALP · Disease control, out-degree [1,20] graph | solvability: 124.7s, 5816731 constraints | Helped |
| RR-ALP policy vs reactive copystate heuristic | disease control policy · 50 nodes, 25 agents | mean return: roughly a factor of 3 | Helped |
| RR-ALP policy vs copystate heuristic | disease control policy · 30 nodes, 15 agents | mean return | Helped |
Closest papers by meaning
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · similarity 0.84)
- Factored Online Planning in Many-Agent POMDPs (AAAI 2024 · similarity 0.84)
- Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization (ICML 2025 · similarity 0.83)
- Prospective Side Information for Latent MDPs (ICML 2024 · similarity 0.83)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.82)
- Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs (NeurIPS 2025 · similarity 0.82)
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.