Continuous Reinforcement Learning With Knowledge-Inspired Reward Shaping for Autonomous Cavity Filter Tuning.
Zhiyang WangYongsheng OuXinyu WuWei FengPublished in: CBS (2018)
Keyphrases
- reinforcement learning
- reward shaping
- complex domains
- domain knowledge
- knowledge base
- prior knowledge
- state space
- knowledge acquisition
- domain experts
- knowledge based systems
- reinforcement learning algorithms
- markov decision processes
- learning algorithm
- optimal policy
- transfer learning
- function approximation
- temporal difference
- supervised learning
- multi agent systems
- decision making