Deep reinforcement learning for multi-objective game strategy selection.
Ruhao JiangYanchen DengYingying ChenHe LuoBo AnPublished in: Comput. Oper. Res. (2024)
Keyphrases
- multi objective
- reinforcement learning
- selection strategy
- optimal strategy
- multi objective optimization
- evolutionary algorithm
- optimization algorithm
- selection strategies
- pareto optimal
- game playing
- computer games
- genetic algorithm
- objective function
- particle swarm optimization
- selection algorithm
- video games
- nsga ii
- multiple objectives
- temporal difference
- game design
- learning process
- bi objective
- reinforcement learning algorithms
- game theory
- nash equilibrium
- temporal difference learning
- conflicting objectives
- two player games
- dynamic programming
- selection criterion
- optimal control
- mixed strategy
- optimum design
- game ai
- evolutionary game
- model free
- game play
- serious games
- educational games
- neural network
- function approximation
- decision problems
- markov decision processes
- virtual world
- state space
- decision making
- learning algorithm
- machine learning