AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning

Minchao Wu, Michael Norrish, Christian Walder, Amir Dezfouli

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 8 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
Learn proof search jointly with tactic and argument selection, including learned backtrackingTacticZero · HOL4 test problems# theorems proved: 132 vs 112Improved
Replace learned proof search with stochastic BFS, branching factor 2 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 99Hurt
Replace learned proof search with stochastic BFS, branching factor 3 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 79Hurt
Replace learned proof search with top-k BFS, branching factor 2 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 116Hurt
Replace learned proof search with top-k BFS, branching factor 3 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 92Hurt
Replace learned proof search with stochastic DFS, branching factor 2 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 83Hurt
Replace learned proof search with stochastic DFS, branching factor 3 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 96Hurt
Replace learned proof search with top-k DFS, branching factor 2 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 86Hurt
Replace learned proof search with top-k DFS, branching factor 3 (ablation)TacticZero · HOL4 test problems# proved: 132 -> 90Hurt
Replace learned proof search with greedy latest-fringe expansion (ablation)TacticZero · HOL4 test problems# proved: 132 -> 112Hurt

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