Cognition · Model asset
Tabular Value Function
Model assetCognitionCognition & Memoryarc:TabularValueFunction
A learned policy model stored as a table holding one value estimate per state-action pair (Q-table).
Responsibility. Stores a Q-value for every state-action pair.
Also known as: Q-table
Variant of Learned Decision Policy abstract
When to choose. Choose when the state-action space is small and discrete enough to enumerate and visit.
Relationships
alternative to variability
Quantitative guidance
As stated by the sources; verify before use.
- A 4x4 grid world with 4 actions needs a 64-entry Q-table; an 84x84x3 pixel observation space has 256^(84x84x3) states, making tables infeasible (Ch5.12).
Classification
- Patterns
- Tabular Q-learning
Sources
- Ch5.12: T. Nguyen, "Learning-Based Decision Making Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.12. ISBN: 9798244538229.