A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems.
Rafael Figueiredo PrudencioMarcos Ricardo Omena Albuquerque MáximoEsther Luna ColombiniPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- open problems
- reinforcement learning
- multidatabase transaction management
- database theory
- long standing
- function approximation
- reinforcement learning algorithms
- multi agent
- learning algorithm
- machine learning
- state space
- markov decision processes
- hierarchical structure
- learning process
- literature review
- model free
- computational advertising
- robotic control
- learning problems
- real time
- multi agent systems
- reward function
- dynamic programming
- multi agent reinforcement learning
- policy search
- neural network
- databases