The Sample Complexity of Teaching by Reinforcement on Q-Learning.
Xuezhou ZhangShubham Kumar BhartiYuzhe MaAdish SinglaXiaojin ZhuPublished in: AAAI (2021)
Keyphrases
- reinforcement learning
- learning process
- function approximation
- learning environment
- continuous state and action spaces
- multi agent
- neural network
- state space
- learning analytics
- cooperative
- learning systems
- computer programming
- dynamic programming
- optimal policy
- learning algorithm
- distance learning
- distance education
- teacher education
- reinforcement learning algorithms
- cooperative learning
- online learning
- agent receives
- markov decision processes
- higher education
- hybrid learning
- model free
- e learning
- science education
- action selection
- problem based learning
- educational technology
- function approximators
- temporal difference learning
- reinforcement learning methods
- potential field