Adaptive Optimal Control for Stochastic Multiplayer Differential Games Using On-Policy and Off-Policy Reinforcement Learning.
Mushuang LiuYan WanFrank L. LewisVictor G. LopezPublished in: IEEE Trans. Neural Networks Learn. Syst. (2020)
Keyphrases
- optimal control
- actor critic
- reinforcement learning
- optimal control problems
- stochastic control
- infinite horizon
- control problems
- policy iteration algorithm
- brownian motion
- optimal policy
- dynamic programming
- computer games
- policy gradient
- educational games
- control policies
- rl algorithms
- online game
- policy iteration
- feedback control
- serious games
- game play
- average cost
- control strategy
- partially observable
- markov decision processes
- imperfect information
- state space
- markov decision process
- mobile games
- finite horizon
- action selection
- function approximation
- adaptive control
- state dependent
- function approximators
- markov decision problems
- temporal difference
- periodic review
- stochastic demand
- approximate dynamic programming
- control law
- video games
- role playing game
- partially observable markov decision processes
- game playing
- machine learning
- model free
- action space
- stochastic process