Average stochastic games for continuous-time jump processes.
Qingda WeiXian ChenPublished in: Oper. Res. Lett. (2021)
Keyphrases
- stochastic games
- markov chain
- nash equilibria
- markov decision processes
- multiagent reinforcement learning
- multi agent
- robust optimization
- multiagent systems
- reinforcement learning algorithms
- finite state
- average reward
- average cost
- infinite horizon
- optimal control
- nash equilibrium
- state space
- neural network
- learning automata
- probability distribution
- imperfect information
- cooperative
- repeated games
- reinforcement learning