A game theoretic approach to curriculum reinforcement learning.
Michalis SmyrnakisLan HoangPublished in: ICTAI (2022)
Keyphrases
- reinforcement learning
- function approximation
- high school
- state space
- multi agent
- reinforcement learning algorithms
- optimal policy
- temporal difference
- markov decision processes
- professional development
- cooperative learning
- multi agent reinforcement learning
- neural network
- stochastic approximation
- optimal control
- model free
- action selection
- learning objects
- learning environment
- temporal difference learning
- learning algorithm
- machine learning