The evolutionary dynamics of soft-max policy gradient in multi-agent settings

DOI10.1016/J.TCS.2024.115011MaRDI QIDQ6658313zbMATH OpenFDO

Authors Martino Bernasconi, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Francesco Trovò

Publication date 8 January 2025

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.TCS.2024.115011

zbMATH Keywords

evolutionary game theorygame theorymultiagent learningreinforcement learning

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Recommendations

• On gradient-based learning in continuous games
• Extended replicator dynamics as a key to reinforcement learning in multi-agent systems.
• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• scientific article; zbMATH DE number 1931819
• The dynamics of multi-agent reinforcement learning

Cites work

• Differential dynamical systems
• Evolutionary Games and Population Dynamics
• Evolutionary Selection in Normal-Form Games
• scientific article; zbMATH DE number 5869530 (Why is no real title available?)
• scientific article; zbMATH DE number 2017728 (Why is no real title available?)
• scientific article; zbMATH DE number 903638 (Why is no real title available?)
• scientific article; zbMATH DE number 7064064 (Why is no real title available?)
• scientific article; zbMATH DE number 3193939 (Why is no real title available?)
• Learning through reinforcement and replicator dynamics
• Learning, regret minimization, and equilibria
• Local stability under evolutionary game dynamics
• Non-cooperative games
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Stable games and their dynamics
• Stochastic Games
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• Sur une manière d'étendre le théorème de la moyenne aux équations différentielles du premier ordre.
• The logic of animal conflict
• The multiplicative weights update method: a meta-algorithm and applications
• The replicator equation and other game dynamics

This page was built for publication: The evolutionary dynamics of soft-max policy gradient in multi-agent settings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6658313)