AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforcement Learning of Theorem Proving

Cezary Kaliszyk, Josef Urban, Henryk Michalewski, Miroslav Olšák

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 15 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
Add jointly learned policy and value guidance with UCTrlCoP · Miz40 testproblems proved: 1143 -> 1624Improved
Add jointly learned policy and value guidance with UCTrlCoP · M2kproblems proved: 876 -> 1235Improved
Use learned policy only, retaining heuristic value instead of jointly learning value (ablation)rlCoP · M2kproblems proved: 1235 -> 1087Hurt
Use learned value only and remove learned policy (ablation)rlCoP · M2kproblems proved: 1235 -> 1144Hurt
Add learned policy guidance while keeping heuristic state values (ablation)rlCoP with UCT · M2kproblems proved: 770 -> 1087Improved
Add learned value guidance without learned policy (ablation)rlCoP with UCT · M2kproblems proved: 770 -> 856Improved
Replace iterative deepening with unguided random search (ablation)bare prover · M2kproblems proved: 876 -> 434Hurt
Add UCT with simple goal-counting evaluation, but no learned policy or value (ablation)bare prover · M2kproblems proved: 434 -> 770Improved
Add UCT with simple goal-counting evaluation, but no learned policy or value (ablation)bare prover · Miz40 testproblems proved: 431 -> 804Improved
Use the jointly learned policy and value from iteration 5 rather than the 10-iteration result (ablation)rlCoP · Miz40 testproblems proved: 1624 -> 1621No clear effect

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