Mastering Complex Coordination through Attention-based Dynamic Graph
The coordination between agents in multi-agent systems has become a popular topic in many fields. To catch the inner relationship between agents, the graph structure is combined with existing methods and improves the results. But in large-scale tasks with numerous agents, an overly complex graph would lead to a boost in computational cost and a decline in performance. Here we present DAGMIX, a novel graph-based value factorization method. Instead of a complete graph, DAGMIX generates a dynamic graph at each time step during training, on which it realizes a more interpretable and effective combining process through the attention mechanism. Experiments show that DAGMIX significantly outperforms previous SOTA methods in large-scale scenarios, as well as achieving promising results on other tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning to Coordinate Manipulation Skills via Skill Behavior Diversification
When mastering a complex manipulation task, humans often decompose the task into sub-skills of their body parts, practice the sub-skills independently, and then execute the sub-skills together. Similarly, a robot with mu…
Can Large Language Models Master Complex Card Games?
Complex games have long been an important benchmark for testing the progress of artificial intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess, garnering widespread soc…
BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action…
Autonomous DrivingPredictive Strategies for the Control of Complex Motor Skills: Recent Insights into Individual and Joint Actions
Humans perform exquisite sensorimotor skills, both individually and in teams, from athletes performing rhythmic gymnastics to everyday tasks like carrying a cup of coffee. The "predictive brain" framework suggests that m…
Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency
We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear regression baseline, we introduce Gaussi…
Computational EfficiencyIn-Context LearningMambaregression