Finite horizon linear quadratic dynamic games for discrete-time stochastic systems with N-players.
Huai-Nian ZhuCheng-Ke ZhangPublished in: Oper. Res. Lett. (2016)
Keyphrases
- finite horizon
- stochastic systems
- linear quadratic
- infinite horizon
- optimal policy
- optimal control
- closed loop
- vector valued
- markov decision processes
- multistage
- reinforcement learning
- steady state
- dynamical systems
- finite state
- long run
- stochastic models
- state space
- probability distribution
- dynamic programming
- search space