Extremal Shift Rule for Continuous-Time Zero-Sum Markov Games.
Yurii V. AverboukhPublished in: Dyn. Games Appl. (2017)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- state space
- markov decision process
- reinforcement learning
- control problems
- optimal control
- stochastic games
- multiagent systems
- markov chain
- multi agent
- optimal policy
- nash equilibrium
- finite state
- cooperative
- dynamic programming
- dynamical systems
- learning algorithm
- reward function
- game theory
- optimal stopping
- function approximation
- multi robot
- control strategy
- infinite horizon
- model free
- temporal difference
- average cost
- incomplete information
- autonomous agents