Deep Reinforcement Learning Task Assignment Based on Domain Knowledge.
Jiayi LiuGang WangXiang-Ke GuoSiyuan WangQiang FuPublished in: IEEE Access (2022)
Keyphrases
- domain knowledge
- reinforcement learning
- function approximation
- domain experts
- learned knowledge
- prior knowledge
- optimal policy
- state space
- temporal difference
- reinforcement learning algorithms
- background knowledge
- aerial vehicles
- dynamic programming
- markov decision processes
- training data
- learning algorithm
- domain models
- temporal difference learning
- domain specific knowledge
- previously learned
- domain theory
- multi robot
- multi agent
- learning problems
- transfer learning
- deep learning
- semantic information
- expert systems
- knowledge base
- policy search
- real time