Value Function Approximation in Zero-Sum Markov Games.
Michail G. LagoudakisRonald ParrPublished in: UAI (2002)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov decision process
- reinforcement learning
- control problems
- stochastic games
- multiagent systems
- state space
- nash equilibrium
- multi agent
- cooperative
- optimal policy
- finite state
- dynamic programming
- policy iteration
- learning algorithm
- optimal stopping
- finite horizon
- adaptive control
- temporal difference learning
- average cost
- model free
- infinite horizon
- optimal control
- function approximation
- initial state
- control system
- multi robot
- dynamic environments