Stationary Equilibria of Mean Field Games with Finite State and Action Space.
Berenice Anne NeumannPublished in: Dyn. Games Appl. (2020)
Keyphrases
- finite state
- action space
- markov decision processes
- nash equilibria
- action sets
- continuous time bayesian networks
- stationary policies
- game theoretic
- game theory
- nash equilibrium
- stochastic games
- continuous state
- state space
- optimal policy
- markov chain
- reinforcement learning
- non stationary
- long run
- dynamic programming
- policy iteration
- decision problems
- markov decision process
- fixed point
- state action
- reinforcement learning algorithms
- average cost
- average reward
- stochastic processes
- partially observable markov decision processes
- infinite horizon
- markov random field
- em algorithm
- cooperative
- single agent
- real valued
- markov decision problems
- belief networks
- partially observable
- maximum likelihood
- multi agent systems
- dynamical systems