Engineering design optimisation using reinforcement learning with episodic controllers.
Jun YangZhenbo ChengGang XiaoXuesong XuYaming WangHaonan DingDiting ZhouPublished in: Cogn. Comput. Syst. (2022)
Keyphrases
- engineering design
- reinforcement learning
- artificial intelligence
- conceptual design
- state space
- function approximation
- reinforcement learning algorithms
- design theory
- model free
- optimal policy
- computer science and artificial intelligence
- automated design
- genetic algorithm
- engineering problems
- engineering education
- design process
- markov decision processes
- multi agent
- temporal difference
- control strategies
- learning algorithm
- learning styles
- optimal control
- dynamic programming
- action selection
- learning process
- control policies
- knowledge discovery
- control system
- learning environment
- machine learning