Utile Coordination: Learning Interdependencies Among Cooperative Agents

By Jelle R. Kok, Pieter Jan't Hoen, Bram Bakker, Nikos A. Vlassis. 2005

75 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. Y. Liu
2. Yujing Hu
3. Yang Gao
4. Yingfeng Chen
5. Sam Devlin
6. Changjie Fan
7. Chao Yu
8. Daniel Kudenko

Citations in the corpus

• Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns (2019, methodology): “…coordination graphs, recent work focuses on automatically identifying interaction areas during the learning process and can be applied to more general learning tasks [De Hauwere et al. , 2010; Hauwere et al. , 2011; Kok et al. , 2005; Melo and Veloso, 2009; Melo and Veloso, 2011; Yu et al. , 2015].”
• Multi-agent Reinforcement Learning: An Overview (2010, background): “The agents learn social conventions in [11], role assignments in [81], and the structure of the coordination graph (see Section 5.1) together with the local Q-functions in [60].”
• Context-sensitive reward shaping for sparse interaction multi-agent systems (2016, background): “Most research around these sparse interactions focusses on learning when agents should coordinate their actions (Kok et al ., 2005) or learning when agents should augment their state space to include information from other agents (Melo & Veloso, 2009; de Hauwere et al ., 2010).”
• Decentralized MDPs with sparse interactions (2011, background): “Other works use coordination graphs to compactly represent dependences between the actions of different agents, thus capturing the local interaction between them [6,7].”
• A Comprehensive Survey of Multiagent Reinforcement Learning (2008, unknown): “the structure of the coordination graph together with the local Q-functions in [83].”
• Learning in Multi-agent Systems with Sparse Interactions by Knowledge Transfer and Game Abstraction (2015, background): “Earlier work adopts coordination graphs (CG) to represent the interactions between agents [7, 8, 13, 14].”
• Multiagent Learning of Coordination in Loosely Coupled Multiagent Systems (2015, background): “These approaches, however, are based on pr ior knowledge of each agent’s individual optimal policy [23] or on the assumptions of agents’ full observability of the joint-sta te and/or joint-action of other agents [20], [22], [24].”