Multiagent learning in the presence of memory-bounded agents

By Doran Chakraborty, Peter Stone. 2013

44 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Statistical and Nonlinear Physics

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

In Management Science and Operations Research

In Statistical and Nonlinear Physics

Citations in the corpus

Learning with Opponent-Learning Awareness (2017, methodology): “By comparing a set of models with different history lengths, Chakraborty and Stone [7] propose a method to learn a best response to memory bounded agents with fixed policies.”
An exploration strategy for non-stationary opponents (2017, methodology): “Since memory bounded opponents are a special case of opponents, different algorithms were specially developed to be used against these agents [11,13].”
Learning against sequential opponents in repeated stochastic games (2017, background): “Learning to act in multiagent systems has received attention mainly from game theory, focused on algorithms that converge to the Nash equilibrium [2, 6, 7]; and from reinforcement learning, focused on acting optimally in stochastic scenarios with limited a priori information but online observations…”
Lenient Learning in Independent-Learner Stochastic Cooperative Games (2016, background): “CMLeS provides different performance guarantees depending on different set of agents in the game (Chakraborty and Stone, 2013a,b).”
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity (2017, background): “…in the form of expected rewards (Littman, 1994; Johanson et al., 2007; Johanson and Bowling, 2009; Powers et al., 2007; Crandall and Goodrich, 2011; Chakraborty and Stone, 2013; Elidrisi et al., 2014; Damer and Gini, 2017) or regret bounds (Yu and Mannor, 2009b; Besbes et al., 2014).”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, methodology): “Essentially the same method can be used to model agents which condition their choices on abstract feature vectors derived from the history (Chakraborty and Stone, 2013).”