Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games Using Baselines.
Martin SchmidNeil BurchMarc LanctotMatej MoravcikRudolf KadlecMichael BowlingPublished in: AAAI (2019)
Keyphrases
- variance reduction
- monte carlo
- regret minimization
- extensive form games
- influence diagrams
- nash equilibrium
- game theoretic
- importance sampling
- decision problems
- quasi monte carlo
- markov chain
- multi agent
- particle filter
- monte carlo tree search
- game theory
- machine learning
- graphical models
- support vector machine
- bayesian networks