Generalised weakened fictitious play

By David S. Leslie, Edmund J. Collins. 2006

174 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Safety Research, 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 Management Science and Operations Research

In Safety Research

In Sociology and Political Science

Citations in the corpus

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games (2016, background): “Leslie and Collins (2006) introduced generalised weakened ﬁctitious play.”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “Computing approximate responses is more computationally feasible, and fictitious play can handle approximations [42, 61].”
Open-ended Learning in Symmetric Zero-sum Games (2019, background): “A closely related algorithm is ﬁctitious (self-)play (Brown, 1951; Leslie & Collins, 2006; Heinrich et al., 2015).”
Learning of coordination: exploiting sparse interactions in multiagent systems (2009, background): “This fact and the aforementioned independence of the components of Qk associated with different xk makes the learning of Qk similar to a generalized fictitious play process [12].”
Joint Strategy Fictitious Play with Inertia for Potential Games (2005, background): “Convergence of player choices when all players use an RL-like algorithm is proved for identical interest games [22]–[24] assuming that learning takes place at multiple time scales.”
Decentralized MDPs with sparse interactions (2011, background): “This fact and the aforementioned independence of the components of Q I k associated with different x̄k makes the learning of Q I k similar to a generalized fictitious play process [33].”
Fictitious Self-Play in Extensive-Form Games (2015, unknown): “A behavioural strategy π induces a realization plan xπ(σu) = ∏ (u′,a)∈σu π(u ′, a), where the notation (u′, a) disambiguates actions taken at different information states.”
Self-play Monte-Carlo tree search in computer poker (2014, background): “It has similarities to generalised weakened fictitious play (Leslie and Collins 2006), for which convergence results have been established for some types of games, e.”
Active Learning and Intrinsically Motivated Exploration in Robots : Advances and Challenges (2010, background): “Results have shown that it is possible to learn in a multiagent scenario even without knowledge of the other's actions and even without knowing that there is another agent [56], [57].”
Guest Editorial Active Learning and Intrinsically Motivated Exploration in Robots: Advances and Challenges (2010, background): “Results have shown that it is possible to learn in a multiagent scenario even without knowledge of the other’s actions and even without knowing that there is another agent [56], [57].”