Solving Sparse Delayed Coordination Problems in Multi-Agent Reinforcement Learning

By Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé. 2011

14 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

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

In Artificial Intelligence

1. Yujing Hu
2. Yang Gao
3. Y. Liu
4. Yann-Michaël De Hauwere
5. Yingfeng Chen
6. Changjie Fan
7. Bo An
8. Sam Devlin

In Management Science and Operations Research

1. Yujing Hu
2. Yang Gao
3. Yann-Michaël De Hauwere
4. Bo An
5. Sam Devlin
6. Daniel Kudenko
7. Ann Nowé
8. Y. Liu

Citations in the corpus

• Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns (2019, methodology): “Several works [De Hauwere et al. , 2010; Hauwere et al. , 2011; Hu et al. , 2015] investigate how to reutilize available knowledge to improve learning algorithms.”
• Learning in Multi-agent Systems with Sparse Interactions by Knowledge Transfer and Game Abstraction (2015, methodology): “Note that a similar problem has been investigated in CQlearning [4] and FCQ-learning [9].”
• Context-sensitive reward shaping for sparse interaction multi-agent systems (2016, methodology): “We build upon Future Coordinating Q-learning (FCQ-learning) (de Hauwere et al ., 2011b), which is capable of detecting these future coordination problems and extend it by means of context-sensitive reward shaping; a novel design of potential functions for reward shaping.”
• A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint (2020, unknown): “proposed CQ-learning [18] and FCQ-learning [19].”