World Hyper-Heuristic: A novel reinforcement learning approach for dynamic exploration and exploitation.
Arman DaliriMahmoud AlimoradiMahdieh ZabihimayvanReza SadeghiPublished in: Expert Syst. Appl. (2024)
Keyphrases
- reinforcement learning
- hyper heuristics
- exploration exploitation tradeoff
- action selection
- active exploration
- dynamic environments
- state space
- machine learning
- neural network
- function approximation
- timetabling problem
- lower bound
- autonomous learning
- exploration strategy
- learning algorithm
- dynamic programming
- special case
- upper bound
- genetic programming
- optimal policy
- search strategies
- evolutionary algorithm