Research map / Reinforcement learning / MDPs and planning
Learning for Decentralized Control of Multiagent Systems in Large, Partially-Observable Stochastic Environments
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 |
|---|---|---|---|
| learn PoEM controller from 1000 hand-coded-policy trajectories instead of using the hand-coded policy | PoEM · SAR domain | mean reward: 4.22 -> greater than 5 | Helped |
| add 5% noise to heuristic policy for training data (ablation) | PoEM · SAR domain | mean reward | Helped |
| increase number of training episodes K (30, 100, 300) (ablation) | PoEM · NAMO | cumulative reward | Helped |
| use more than 100 training samples (ablation) | PoEM · SAR domain | mean reward | Helped |
| vary FSC node count |Qn| from 4 to 50 (ablation) | PoEM · SAR domain | cumulative reward | No clear effect |
| use too small a controller size |Qn| (ablation) | PoEM · SAR domain | cumulative reward | Hurt |
Closest papers by meaning
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior (ICLR 2024 · similarity 0.89)
- Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach (AAAI 2025 · similarity 0.88)
- Scalable Policy-Based RL Algorithms for POMDPs (NeurIPS 2025 · similarity 0.87)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.87)
- Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems (NeurIPS 2025 · similarity 0.87)
- Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays (NeurIPS 2025 · similarity 0.86)
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.