AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search

Yelong Shen, Jianshu Chen, Po-Sen Huang, Yuqing Guo, Jianfeng Gao

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 58 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
Combine MCTS trajectory generation with off-policy Q-learning policy improvementM-Walk on Three Glass Puzzle · Three Glass Puzzleaccuracy: (49.0 ± 2.6)% -> (99.0 ± 1.0)%Improved
Replace MCTS with beam search at test time (ablation)M-Walk · Three Glass Puzzle testaccuracy: 99.0 (1.0) -> 71.7 (4.5)Hurt
Use the M-Walk neural architecture rather than MINERVA's architecture (ablation)PG-Walk · NELL995MAP: 87.6 -> 88.9Improved
Add MCTS to policy-gradient training and beam-search testing (ablation)M-Walk on NELL995 · NELL995MAP: 88.9 -> 89.9Improved
Add MCTS trajectory generation to Q-learning-only training (ablation)M-Walk on NELL995 · NELL995MAP: 87.8 -> 89.9Improved
Add MCTS to policy-gradient training and beam-search testing (ablation)M-Walk on WN18RR · WN18RRHITS@1: 39.3 (0.2) -> 41.4 (0.1)Improved
Add MCTS trajectory generation to Q-learning-only training (ablation)M-Walk on WN18RR · WN18RRHITS@1: 38.2 (0.3) -> 41.4 (0.1)Improved
Add MCTS to policy-gradient training and beam-search testing (ablation)M-Walk on FB15k-237 · FB15k-237HITS@1: 14.8(0.2) -> 16.5(0.3)Improved
Add MCTS trajectory generation to Q-learning-only training (ablation)M-Walk on FB15k-237 · FB15k-237HITS@1: 15.5(0.2) -> 16.5(0.3)Improved
Use M-Walk rather than ConvEWN18RR · WN18RRHITS@3: 44.7 (0.2) vs 44.5 (0.2)No clear effect
Use M-Walk rather than embedding-based baselinesFB15k-237 · FB15k-237HITS@1: 16.5(0.3) vs 23.3(0.4)Hurt
Increase the number of MCTS rollouts (ablation)M-Walk on Three Glass Puzzle · Three Glass Puzzle testaccuracy: 18.0 (1.7) -> 99.0 (1.0)Improved

Later papers that compared with this method

1 later accepted paper reports M-walk as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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