Towards Understanding Linear Value Decomposition in Cooperative Multi-Agent Q-Learning

By Jianhao Wang, Zhizhou Ren, Beining Han, Chongjie Zhang. 2020

25 citations recorded by the source corpus.

How researchers see this paper

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

1. Tonghan Wang
2. Bei Peng
3. Christian Schröder de Witt
4. Tabish Rashid
5. Jianhao Wang
6. Shimon Whiteson
7. Yihan Wang
8. Tarun Gupta

Citations in the corpus

• RODE: Learning Roles to Decompose Multi-Agent Tasks (2020, methodology): “However, learning roles from scratch might not be easier than learning without roles, as directly finding an optimal decomposition suffers from the same problem as other CTDE learning methods – searching in the large joint space with substantial exploration (Wang et al., 2020c).”
• QPLEX: Duplex Dueling Multi-Agent Q-Learning (2020, methodology): “We evaluate the performance of QPLEX in both didactic problems proposed by prior work [8,11] and a range of unit micromanagement benchmark tasks in StarCraft II [10].”
• FACMAC: Factored Multi-Agent Centralised Policy Gradients (2020, background): “This shows the convergence advantages of policy gradient methods in this type of multi-agent settings [40].”
• Off-Policy Multi-Agent Decomposed Policy Gradients (2020, background): “Multi-agent policy gradient algorithms enjoy stable convergence properties compared to value-based methods (Gupta et al., 2017; Wang et al., 2020a) and can extend MARL to continuous control problems.”