Continuous-Time Markov Games with Asymmetric Information.
Fabien GensbittelPublished in: Dyn. Games Appl. (2019)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- state space
- markov decision process
- reinforcement learning algorithms
- control problems
- optimal control
- reinforcement learning
- markov chain
- multiagent systems
- dynamic programming
- finite state
- infinite horizon
- policy iteration
- cooperative
- dynamical systems
- nash equilibrium
- stochastic games
- optimal policy
- finite horizon
- model free
- temporal difference learning
- stochastic processes
- multi agent
- learning algorithm
- function approximation
- adaptive control
- average reward
- optimal stopping