Coordination and Adaptation in Impromptu Teams

By Michael H. Bowling, Peter Mccracken. 2005

90 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.

Citations in the corpus

The Hanabi Challenge: A New Frontier for AI Research (2019, background): “Notably, humans collaborate successfully without relying on prior coordination or knowing the policy of their teammates, commonly referred to as the ad-hoc team setting [16, 17].”
A survey and critique of multiagent deep reinforcement learning (2018, background): “particular in the context of self-play learning and ad-hoc teams [306, 307, 308].”
A game-theoretic model and best-response learning method for ad hoc coordination in multiagent systems (2013, background): “For example, in [3,4] it is assumed that all agents follow complex plans which specify roles and synchronised action sequences, and in [6] and affiliated works it is assumed that the behaviours of the other agents are a priori known and fixed, and that all agents have common payoffs.”
Reasoning about Hypothetical Agent Behaviours and their Parameters (2017, background): “An important open problem in multi-agent systems is the design of autonomous agents that can quickly and effectively interact with other agents when there is no opportunity for prior coordination, such as shared world models and communication protocols [2, 11, 37].”
Making friends on the fly: Cooperating with new teammates (2017, unknown): “A work that looks at more complex coordination in ad hoc teams is that of Bowling and McCracken [18].”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, background): “This is important in problems of ad hoc (or impromptu) teamwork (Stone et al., 2010; Bowling and McCracken, 2005), in which an agent has to collaborate “on the ﬂy” with an established but previously unknown team, without opportunities for prior coordination with the team members.”
Three years of the RoboCup standard platform league drop-in player competition (2016, unknown): “In the robot soccer domain, Bowling andMcCracken [3] proposemethods for coordinating an agent that joins an unknown, pre-existing team.”