Bias and overtaking equilibria for zero-sum continuous-time Markov games.
Tomás Prieto-RumeauOnésimo Hernández-LermaPublished in: Math. Methods Oper. Res. (2005)
Keyphrases
- markov games
- nash equilibrium
- markov decision processes
- multiagent reinforcement learning
- control problems
- state space
- stochastic games
- markov decision process
- reinforcement learning algorithms
- optimal control
- nash equilibria
- reinforcement learning
- game theory
- game theoretic
- games with incomplete information
- multiagent systems
- repeated games
- optimal policy
- dynamical systems
- long run
- markov chain
- cooperative
- fixed point
- dynamic programming
- multi agent
- average reward
- finite state
- policy iteration
- stochastic processes
- imperfect information
- state variables
- function approximation
- incomplete information