AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning

Lei Wang, Dongxiang Zhang, Lianli Gao, Jingkuan Song, Long Guo, Heng Tao Shen

AAAI 2018 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 126 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
DQN-based expression tree construction vs prior SOTAmath word problem solver · Average of AI2/IL/CCaccuracy: 64.6 -> 75.4Improved
DQN-based expression tree constructionmath word problem solver · ILaccuracy: 74.8 -> 73.3Hurt
add re-order mechanism (ablation)MathDQN · CCaccuracy: 63.7% to 75.5%Improved
add re-order mechanism (ablation)MathDQN · AI2accuracy: 78.5 -> 78.5No clear effect
Q-learning instead of Sarsa (ablation)MathDQN · CCaccuracy: 71.8 -> 75.5Improved
RL framework instead of supervised operator classifier (ablation)MathDQN · AI2accuracy: 76.2 -> 78.5Improved
add context featureUnitDep · CCaccuracy: 47.3% to 53.5%Improved
add context featureUnitDep · AI2accuracy: 74.7% to 56.2%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy