Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory
From MaRDI portal
Publication:2667841
DOI10.1016/j.artint.2021.103653OpenAlexW3113152939MaRDI QIDQ2667841
Stefanos Leonardos, Georgios Piliouras
Publication date: 2 March 2022
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2012.03083
Related Items (1)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- A continuous-time approach to online optimization
- What evolutionary game theory tells us about multiagent learning
- Experience-weighted attraction learning in coordination games: Probability rules, heterogeneity, and time-variation
- Playing safe in coordination games: The roles of risk dominance, payoff dominance, and history of play
- Multiagent learning using a variable learning rate
- \({\mathcal Q}\)-learning
- Equilibrium selection in \(n\)-person coordination games
- Potential games
- Quantal response equilibria for normal form games
- Strategic decompositions of normal form games: zero-sum games and potential games
- The logit-response dynamics
- Self-tuning experience weighted attraction learning in games
- Stability and diversity in collective adaptation
- Zero-Sum Polymatrix Games: A Generalization of Minmax
- Learning in Games via Reinforcement and Regularization
- Evolutionary Dynamics of Multi-Agent Learning: A Survey
- On Best-Response Dynamics in Potential Games
- Intrinsic Robustness of the Price of Anarchy
- Penalty-Regulated Dynamics and Robust Learning Procedures in Games
- Experience-weighted Attraction Learning in Normal Form Games
- On Gradient-Based Learning in Continuous Games
- Complex dynamics in learning complicated games
- Multiplicative updates outperform generic no-regret learning in congestion games
- Individual Q-Learning in Normal Form Games
- Prediction, Learning, and Games
This page was built for publication: Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory
