Accelerating wargaming reinforcement learning by dynamic multi-demonstrator ensemble.
Liwei DongNi LiHaitao YuanGuanghong GongPublished in: Inf. Sci. (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- neural network
- data sets
- training data
- markov decision processes
- ensemble methods
- function approximation
- dynamically changing
- reinforcement learning algorithms
- ensemble classifier
- temporal difference
- action selection
- random forests
- ensemble learning
- learning problems
- dynamic programming
- training set
- data structure
- website