Continual Graph Multi-Agent Reinforcement Learning
To fill this gap, we propose Continual Graph Multi-Agent Reinforcement Learning (CGMARL), a novel framework for CMARL problems in which task sequences are mapped into a series of attributed graphs, each modeling a task-specific structure.
ProofPaper ↗
Key points
- In Continual Multi-Agent Reinforcement Learning (CMARL), agents learn cooperative policies across sequences of tasks, aiming to adapt effectively to new tasks while preserving the ability to solve previously encountered ones.
- In CGMARL, each graph determines the environment dynamics (next states and/or rewards) and the number of agents for the corresponding task.
- Then, we present Graph-based Formation (GRAFO), the first CGMARL benchmark, and show how forgetting arises in this setting.
- Finally, to address this limitation, we propose Frozen Graph Encoder (FROG), a method that relies on a frozen graph backbone to preserve past structural information in graph-based CMARL policies.
Sources (1)
- [1]Continual Graph Multi-Agent Reinforcement LearningarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 03:56 PM
To fill this gap, we propose Continual Graph Multi-Agent Reinforcement Learning (CGMARL), a novel framework for CMARL problems in which task sequences are mapped into a series of attributed graphs, each modeling a task-specific structure.
In Continual Multi-Agent Reinforcement Learning (CMARL), agents learn cooperative policies across sequences of tasks, aiming to adapt effectively to new tasks while preserving the ability to solve previously encountered ones.
Extractive summary: sentences quoted from the sources.
