Leveraging Granularity: Hierarchical Reinforcement Learning for Pedagogical Policy Induction.
Guojing ZhouHamoon AzizsoltaniMarkel Sanz AusinTiffany BarnesMin ChiPublished in: Int. J. Artif. Intell. Educ. (2022)
Keyphrases
- hierarchical reinforcement learning
- markov decision process
- reward function
- reinforcement learning
- average reward
- optimal policy
- policy iteration
- model free
- markov decision processes
- e learning
- state space
- state abstraction
- learning process
- learning environment
- infinite horizon
- inductive learning
- inductive logic programming
- concept learning
- machine learning
- generative model
- search algorithm