Online learning about other agents in a dynamic multiagent system

How researchers see this paper

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

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017, background): “[13] stressed the importance of being robust to the decision making process of”
A Parametrization of the Auction Design Space (2001, methodology): “This function is used in a study by Hu and Wellman [18].”
An Overview of Cooperative and Competitive Multiagent Learning (2005, background): “More and more complex nested opponent models [77] will probably be the future norm in the MARL agents arms race.”
Cooperative Multi-Agent Learning: The State of the Art (2005, result): “Hu and Wellman [118], Wellman and Hu [290] suggest that when learning models of other agents in a multi-agent learning scenario, the resulting behaviors are highly sensitive to the agents’ initial beliefs.”
Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks (2018, background): “Similar to [30], we define the local state of learning agent i as si ∈ Si which is composed of environment features that are relevant to agent i’s action ai ∈ Ai.”
A Survey of Collectives (2004, background): “They do this to try to ensure that the overall system both moves toward achieving the overall global goal and avoids often deleterious oscillatory behavior [53, 85, 111, 113, 112].”