Zero-Sum Markov Games with Impulse Controls.
Arnab BasuLukasz StettnerPublished in: SIAM J. Control. Optim. (2020)
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
- optimal policy
- nash equilibrium
- cooperative
- learning algorithm
- multi agent
- dynamic programming
- finite state
- model free
- policy iteration
- average cost
- initial state
- finite horizon
- average reward
- optimal control
- function approximation
- reward function
- infinite horizon
- multi robot
- temporal difference learning
- decision problems