Curriculum Reinforcement Learning Based on K-Fold Cross Validation.
Zeyang LinJun LaiXiliang ChenLei CaoJun WangPublished in: Entropy (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- optimal policy
- high school
- reinforcement learning algorithms
- model free
- professional development
- multi agent
- multi agent reinforcement learning
- markov decision processes
- optimal control
- temporal difference learning
- transfer learning
- dynamic programming
- learning algorithm
- physical education
- primary school
- elementary school
- cooperative learning
- case study