Latest Research in Multi-Agent Reinforcement Learning

Top Research Topics in Multi-Agent Reinforcement Learning

• Machine Learning — 268 papers
• Computer Vision and Pattern Recognition — 259 papers
• Artificial Intelligence — 123 papers
• Computation and Language — 62 papers
• Robotics — 31 papers
• Machine Learning — 16 papers
• Multimodal Machine Learning Applications — 13 papers
• Reinforcement Learning in Robotics — 12 papers
• Multiagent Systems — 10 papers
• Systems and Control — 9 papers

Highest-Cited Papers

1. AI Teacher Latent Basis Reorientation
2. Context-Aware visual scene analysis and adaptation for intelligent english tutoring systems
3. Attention Is All You Need: A Technical Review of the Transformer Architecture and Its Impact on Modern Artificial Intelligence
4. Attention Is All You Need: A Technical Review of the Transformer Architecture and Its Impact on Modern Artificial Intelligence
5. Accelerating Q-learning through Efficient Value-Sharing across Actions
6. Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces
7. Reward Shaping based on Trajectory Quality for offline and hybrid reinforcement learning
8. Source-Free Domain Adaptation with Vision-Language Prior
9. CFR variant and iterate reporting in small imperfect-information games
10. Neuromorphic-Inspired Language Identification for Low-Resource Code-Switched Texts Using Spiking Neural Networks
11. Opponent-modeling-enhanced multi-agent reinforcement learning for dynamic games under incomplete information
12. State-based Selection of Expert Policies in Disaster Environments and Reinforcement Learning of a Unified Student Policy via Distillation
13. Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
14. Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models
15. Region-Level Policy Optimization for Fine-grained MLLM Perception
16. Precision autotuning for linear solvers via contextual bandit-based RL
17. CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning
18. Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint
19. L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts
20. EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control

Sub-Regions

• Machine Learning — 271 papers
• Computation and Language — 155 papers
• Robotics — 139 papers
• Information Retrieval — 104 papers
• Artificial Intelligence — 80 papers
• Computer Vision and Pattern Recognition — 63 papers