The OAK architecture contains eight main steps executed in parallel at runtime: learning reward policy and value, generating new state features, creating subproblems from features, solving subproblems to create options, learning transition models for options, ordering features by utility, maintaining metadata and pruning, and planning with the learned models
definitionpending
Speaker
Richard SuttonEvidence Quote
“eight steps done in parallel at runtime...learning policy and value, generating features, creating subproblems, solving them, learning models, ordering features, maintaining metadata, and planning”
Source
Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025— AmiiCreated: 8/11/2026, 7:21:57 AM
Your notes
Loading notes...