Dichotomy value iteration with parallel learning design towards discrete-time zero-sum games.
Jiangyu WangDing WangXin LiJunfei QiaoPublished in: Neural Networks (2023)
Keyphrases
- learning design
- ims ld
- ims learning design
- authoring tool
- learning activities
- learning experience
- learning resources
- e learning
- learning processes
- learning analytics
- learning materials
- learning technologies
- learning management systems
- markov decision processes
- state space
- technology enhanced
- learning objects
- markov chain
- optimal strategy
- modelling language
- learning scenarios
- heuristic search
- learning systems
- finite state
- dynamic programming
- collaborative learning activities
- database
- reinforcement learning