A Proximal/Gradient Approach for Computing the Nash Equilibrium in Controllable Markov Games.
Julio B. ClempnerPublished in: J. Optim. Theory Appl. (2021)
Keyphrases
- nash equilibrium
- markov games
- game theory
- game theoretic
- markov decision processes
- stochastic games
- multiagent reinforcement learning
- nash equilibria
- pure strategy
- mixed strategy
- reinforcement learning algorithms
- markov decision process
- stackelberg game
- worst case
- equilibrium strategies
- special case
- control problems
- finite state
- incomplete information
- resource allocation
- optimal policy
- reinforcement learning