An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games

By Karl Tuyls, Pieter Jan't Hoen, Bram Vanschoenwinkel. 2005

165 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science

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 Sociology and Political Science

Citations in the corpus

Evolutionary Dynamics of Multi-Agent Learning: A Survey (2015, methodology): “Both fields are concerned with dynamic environments with a high level of uncertainty, characterised by the fact that agents lack complete information (Tuyls et al., 2006).”
A Comprehensive Survey of Multiagent Reinforcement Learning (2008, unknown): “One important step forward in understanding how singleagent RL works in multiagent tasks was made recently in [87].”
Neural Replicator Dynamics (2019, unknown): “…MARL have been primarily identiﬁed between the Replicator Dynamics (RD), a standard model in EGT, and simple policy iteration algorithms such as Cross Learning and Learning Automata [4, 5, 65], value-iteration algorithms such as Q-learning in stateless cases [27, 63], and no-regret learning [29].”
The world of independent learners is not markovian (2011, background): “All the recent surveys and many works on multiagent learning mention this fact as a key challenge [5, 35, 21, 24, 38, 10, 6, 32, 39, 26, 13, 40].”
Multi-agent Reinforcement Learning: An Overview (2010, background): “One important step forward in understanding how single-agent RL works in multi-agent tasks was made in [130].”
Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective (2008, methodology): “For a complete mathematical derivation of it, please refer to Tuyls et al. (2006, 2003).”
Opportunities for multiagent systems and multiagent reinforcement learning in traffic control (2009, background): “In fact, this shift fits very well multiagent learning in general and learning in dynamic scenarios (such as traffic control) as already detected in [4,5,81,82].”
What evolutionary game theory tells us about multiagent learning (2007, background): “In the subsequent sections we will explain the basis for these beliefs.”
A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics (2008, methodology): “We are currently investigating alternative methodologies for analyzing dynamics, including the evolutionary dynamics (Tuyls, ’t Hoen, & Vanschoenwinkel, 2006) and Lyapunov stability theory (Khalil, 2002).”