Research map / Multi-agent systems and games / Cooperative multi-agent RL
Bounding the Probability of Resource Constraint Violations in Multi-Agent 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 |
|---|---|---|---|
| add Hoeffding-based reduced resource limits | CMDP · Lottery | violation frequency / expected value | Mixed |
| add dynamic constraint relaxation on top of Hoeffding bound (ablation) | CMDP / Column Generation · Lottery | expected value | Helped |
| add dynamic constraint relaxation on top of Hoeffding bound (ablation) | CMDP · TCL | expected value and violation tolerance fit | Helped |
| use dynamic relaxation instead of unbounded CMDP | CMDP · Maze 5x5 | violations | Helped |
| add column pruning to Column Generation (ablation) | Column Generation · TCL n=100, horizon up to 128 | runtime | Helped |
| use Column Generation with pruning instead of direct CMDP encoding | resource-constrained MMDP · TCL n=100 | runtime | Helped |
| add dynamic relaxation to Hoeffding-bounded planning (ablation) | Column Generation · Synthetic Advertising | violation probability | Helped |
| add Hoeffding reduction in advertising domain (ablation) | Column Generation · Synthetic Advertising | expected value | Hurt |
| increase number of agents with bounded limits | Hoeffding / dynamic bound · TCL | expected value | Helped |
Closest papers by meaning
- Preallocation and Planning Under Stochastic Resource Constraints (AAAI 2018 · similarity 0.91)
- Factored Online Planning in Many-Agent POMDPs (AAAI 2024 · similarity 0.86)
- Belief-State Query Policies for User-Aligned POMDPs (NeurIPS 2024 · similarity 0.86)
- Near-Optimal Sample Complexity for Online Constrained MDPs (NeurIPS 2025 · similarity 0.85)
- Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm (NeurIPS 2025 · similarity 0.85)
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs (NeurIPS 2026 · 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.