Data-Driven Integral Reinforcement Learning for Continuous-Time Non-Zero-Sum Games.
Yongliang YangLiming WangHamidreza ModaresDawei DingYixin YinDonald WunschPublished in: IEEE Access (2019)
Keyphrases
- data driven
- reinforcement learning
- state space
- optimal control
- function approximation
- markov chain
- model free
- dynamical systems
- reinforcement learning algorithms
- optimal strategy
- learning algorithm
- partially observable
- markov processes
- policy iteration
- temporal difference
- imperfect information
- temporal difference learning
- reinforcement learning methods
- iterative learning control
- stochastic processes
- markov decision processes
- dynamic programming
- markov decision process
- genetic algorithm
- control strategy
- perfect information
- multi agent reinforcement learning
- opponent modeling
- semi markov decision process