CESMA: Centralized Expert Supervises Multi-Agents

By Alex Tong Lin, Mark J. Debord, Katia Estabridis, Gary A. Hewer, Stanley J. Osher. 2019

6 citations recorded by the source corpus.

Subfields: LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In LLM Agents & Tool Use

1. Shimon Whiteson
2. Tabish Rashid
3. Jakob N. Foerster
4. Gregory Farquhar
5. Christian Schröder de Witt
6. Wendelin Böhmer
7. Chongjie Zhang

Citations in the corpus

• Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2020, background): “Lin et al. (2019) train a centralised action-value function Q which has access to observations of all agent.”
• MAVEN: Multi-Agent Variational Exploration (2019, background): “Lin et al.[27] first learn a centralised controller to solve the task, and then train the agents to imitate its behaviour.”