Limits RegistryPUBLIC RECORDLimits RegistryResearch Console →Tabular Q-learning converges under finite MDP, sufficient exploration, bounded rewards, and Robbins-Monro step sizes.
The question, scope, and sources behind this Registry record.
Under the recorded reinforcement learning model, establish Q_t converges to Q* almost surely.
Current frontiers derived from accepted Claims.
The accepted equality closes this optimization result.
Assertions tied to evidence, attribution, and review.
The frontier as it changed over time.
Only accepted Claims matching the current specification contribute to the displayed bounds. Strict inequalities remain open; contradictory Claims require editorial review.
No accepted machine-checked reproductions are recorded for this Limit.
Limits Registry. LR-003636. Tabular Q-learning convergence limit. 2026.