Combining reward shaping and hierarchies for scaling to large multiagent systems

By Chris HolmesParker, Adrian K. Agogino, Kagan Tumer. 2016

15 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research, Reinforcement Learning

How researchers see this paper

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

In Computer Networks and Communications

1. Wojciech M. Czarnecki
2. Thore Graepel
3. David Balduzzi
4. Muhammad Ghifary
5. Marc Lanctot
6. Karl Tuyls
7. Vinícius Flores Zambaldi

In Information Systems

1. Thore Graepel
2. Karl Tuyls

In Management Science and Operations Research

1. David Balduzzi
2. Marc Lanctot
3. Wojciech M. Czarnecki
4. Thore Graepel
5. Karl Tuyls
6. Joel Z. Leibo
7. Peter Sunehag
8. Muhammad Ghifary

In Reinforcement Learning

1. Karl Tuyls
2. Shimon Whiteson
3. Joel Z. Leibo
4. Thore Graepel
5. Marc Lanctot
6. Wojciech M. Czarnecki
7. Sergey Levine
8. Vinícius Flores Zambaldi

Citations in the corpus

• Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies (2015, background): “The relation between GProp and the difference-based objective proposed for multiagent learning (Agogino and Tumer, 2008; HolmesParker et al., 2014) is discussed in section 5.4.”
• Value-Decomposition Networks For Cooperative Multi-Agent Learning (2017, background): “Other approaches can be found in Devlin et al. (2014); HolmesParker et al. (2016); Babes et al. (2008).”
• Exploiting Structure and Agent-Centric Rewards to Promote Coordination in Large Multiagent Systems (2014, unknown): “Second, because the second term does not depend on the actions of agent j, any action by agent j that improvesD, also improvesR (the derivatives of D and R with respect to agent j are the same) [18].”