The authors identify a structural barrier ('two-hump' difficulty distribution) in RL for mathematical search problems like the Andrews-Curtis conjecture and propose data generation plus algorithmic enhancements to create solvable intermediate instances, releasing AC-19 and AC-1M datasets.
Accessed: 2025-01-30
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning
The authors identify a structural barrier ('two-hump' difficulty distribution) in RL for mathematical search problems like the Andrews-Curtis conjecture and propose data generation plus algorithmic enhancements to create solvable intermediate instances, releasing AC-19 and AC-1M datasets.