Multiagent-Based Reinforcement Learning for Optimal Reactive Power Dispatch

By Yinliang Xu, Wenxin Liu, Frank T. Ferrese. 2012

136 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Control and Systems Engineering, Electrical and Electronic Engineering

How researchers see this paper

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

In Computational Theory and Mathematics

1. Chris Amato
2. Karl Tuyls
3. Rahul Savani
4. Gregory Palmer
5. Jonathan P. How
6. Daan Bloembergen
7. Shayegan Omidshafiei
8. Jason Pazis

In Control and Systems Engineering

1. Gregory Palmer
2. Jonathan P. How
3. Karl Tuyls
4. Rahul Savani
5. Jason Pazis
6. Chris Amato
7. John L. Vian

In Electrical and Electronic Engineering

1. Chris Amato
2. Jonathan P. How
3. Karl Tuyls
4. Rahul Savani
5. Xueguang Lyu
6. Jianye Hao

Citations in the corpus

• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability (2017, methodology): “Hysteretic Q-learning has enjoyed a strong empirical track record in fully-observable MARL (Xu et al., 2012; Matignon et al., 2012; Barbalios & Tzionas, 2014), exhibiting similar performance as more complex approaches.”
• Lenient Multi-Agent Deep Reinforcement Learning (2017, background): “Hysteretic Q-learning is a form of optimistic learning with a strong empirical track record in fully-observable MA-RL [2, 18, 37].”