A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets.
Gauthier GidelDavid BalduzziWojciech CzarneckiMarta GarneloYoram BachrachPublished in: AISTATS (2021)
Keyphrases
- neural nets
- limited capacity
- nash equilibrium
- nash equilibria
- game theory
- scheduling problem
- feed forward
- game tree
- game theoretic
- imperfect information
- neural network
- operating costs
- back propagation
- artificial neural networks
- cooperative games
- cooperative game
- counter propagation
- asymptotic properties
- learning tasks
- worst case
- video games
- solution concepts
- equilibrium strategies
- minimax search
- game playing
- computer games
- utility function
- learning algorithm
- von neumann
- social welfare
- transfer learning
- special case
- knowledge base
- artificial intelligence