Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning.
Rajarshi DasShehzaad DhuliawalaManzil ZaheerLuke VilnisIshan DurugkarAkshay KrishnamurthyAlexander J. SmolaAndrew McCallumPublished in: CoRR (2017)
Keyphrases
- knowledge base
- reinforcement learning
- knowledge representation systems
- reasoning process
- description logics
- knowledge representation
- knowledge based systems
- reasoning tasks
- inference engine
- answering questions
- expert systems
- function approximation
- machine learning
- knowledge acquisition
- random walk
- open world
- abductive logic programming
- formal representation
- markov decision processes
- reasoning engine
- state space
- model free
- multi agent
- production rules
- commonsense reasoning
- function approximators
- evaluation function
- reinforcement learning algorithms
- temporal difference
- optimal control
- semantic network
- knowledge sources
- optimal policy
- wordnet
- logic programs
- dynamic programming
- bayesian networks
- artificial intelligence