liveBook · Manning

Value

As explained in Applied Reinforcement Learning

A value is an attention vector containing the information contributed by an input element after attention weights are computed.

In attention, each input element contributes a value vector. After query-key scores become softmax weights, each element’s output is a weighted sum of the values, emphasizing information from relevant neighbors. section 9.5

Figure 9.6 The Attention Mechanism — Query, Key, Value.

The diagram shows how queries, keys, and values combine to produce attention outputs. section 9.5

How Applied Reinforcement Learning covers it

How deep it goes
Defines values as vectors and explains their weighted-sum contribution to attention outputs.
Examples
Uses building zones as input elements and considers scaling attention from 8 zones to 80.
What you can do after
Understand how attention weights select and combine information from relevant neighboring zones.
How it connects
Links values to queries, keys, dot-product scores, softmax weights, and attention.

Also explained in

Compare how 15 books explain value →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Applied Reinforcement Learning. The section links point to the parts of the book it draws on.