A reward-respecting sub-problem of feature attainment takes a feature index i, a kappa parameter (intensity of wanting that feature), and creates a problem to drive the world to a state where the feature is high without losing too much main reward, formalized as a policy and termination function that maximize cumulative reward plus the feature value at termination
definitionpending
Speaker
Richard SuttonEvidence Quote
“a reward respecting subpros of feature attainment... the sub problem is to drive the world to a state where the feature is high without losing too much reward”
Source
Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025— AmiiCreated: 8/11/2026, 6:51:29 AM
Your notes
Loading notes...