Neural Math Word Problem Solver with Reinforcement Learning.

Danqing Huang Jing Liu Chin-Yew Lin Jian Yin

Published in: COLING (2018)

Keyphrases

word problems
reinforcement learning
fitted q iteration
grade students
network architecture
function approximation
similar problems
neural network
state space
optimal policy
markov decision processes
learning algorithm
high school
learning process
hong kong
tutoring system
computer assisted
learning activities