Attention Based Reinforcement Learning with Reward Shaping for Knowledge Graph Reasoning.
Sheng WangXiaoying ChenShengwu XiongPublished in: NLPCC (1) (2021)
Keyphrases
- reinforcement learning
- reward shaping
- complex domains
- knowledge base
- knowledge representation
- domain knowledge
- knowledge acquisition
- function approximation
- reasoning process
- random walk
- solving problems
- expert systems
- state space
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- markov decision problems