Research map / Multi-agent systems and games / Cooperative multi-agent RL
Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach
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 fully decentralized regression-based policies instead of no control | OPF on an Arizona distribution grid · Arizona distribution grid simulation | voltage variation | Helped |
| Choose communicated nodes by maximizing mutual information with the target action rather than selecting nodes randomly | Restricted-communication policies · Synthetic Gaussian example | average distortion | Helped |
| Choose communicated nodes by maximizing mutual information with the target action rather than selecting nodes randomly | OPF policies · OPF smaller network | mean squared error distortion | Helped |
| Use fully decentralized regression-based policies instead of centralized optimal control | OPF on an Arizona distribution grid · Arizona distribution grid simulation | suboptimality: 0.15% on average; maximum deviation of 1.6% | Mixed |
Closest papers by meaning
- Learning to Act in Decentralized Partially Observable MDPs (ICML 2018 · similarity 0.89)
- Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming (ICLR 2022 · similarity 0.89)
- Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games (ICLR 2022 · similarity 0.89)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.88)
- Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies (ICML 2024 · similarity 0.88)
- TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient (AAAI 2024 · 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.