Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning.
Rajarshi DasShehzaad DhuliawalaManzil ZaheerLuke VilnisIshan DurugkarAkshay KrishnamurthyAlex SmolaAndrew McCallumPublished in: ICLR (Poster) (2018)
Keyphrases
- knowledge base
- reinforcement learning
- knowledge representation systems
- reasoning process
- knowledge representation
- inference engine
- description logics
- expert systems
- knowledge acquisition
- function approximation
- knowledge based systems
- reasoning tasks
- machine learning
- model free
- answering questions
- optimal policy
- temporal difference
- reinforcement learning algorithms
- multi agent
- artificial intelligence
- reasoning systems
- learning algorithm
- production rules
- shortest path
- abductive logic programming
- logic programming
- learning process
- reasoning engine
- computing least common subsumers
- answering queries
- knowledge representation and reasoning
- correct answers
- action selection
- optimal control
- wordnet
- random walk