Research map / Multi-agent systems and games / Cooperative multi-agent RL
Actor-Attention-Critic for Multi-Agent Reinforcement Learning
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 learned selective attention instead of uniform attention (ablation) | MAAC · Rover-Tower | average reward | Helped |
| Use uniform attention instead of learned selective attention (ablation) | MAAC · Cooperative Treasure Collection | average reward | No clear effect |
| Use uniform attention instead of learned selective attention (ablation) | MAAC · Cooperative Navigation | average reward | No clear effect |
| Use uniform attention instead of learned selective attention (ablation) | MAAC · Rover-Tower | average reward | Hurt |
| Replace the attentive critic with a MADDPG+SAC critic | MAAC · Cooperative Treasure Collection, increasing number of agents | normalized average reward | Mixed |
| Replace the attentive critic with a MADDPG critic | MAAC · Rover-Tower, increasing number of agents | average reward | Hurt |
| Use an attentive centralized critic rather than a MADDPG-style concatenating critic | MAAC · Cooperative Treasure Collection | average reward | Helped |
| Use an attentive centralized critic rather than a DDPG policy unaware of other agents | MAAC · Rover-Tower | average reward | Helped |
Closest papers by meaning
- Multi-Agent Actor-Critic with Hierarchical Graph Attention Network (AAAI 2020 · similarity 0.93)
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (NeurIPS 2017 · similarity 0.92)
- Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games (ICLR 2022 · similarity 0.90)
- Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.89)
- Offline Actor-Critic Reinforcement Learning Scales to Large Models (ICML 2024 · similarity 0.88)
- Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.87)
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.