liveBook · Manning

Node

As explained in Applied Reinforcement Learning

A node is an element in a tree or graph that represents a state, decision point, or piece of information.

A node is an element in a tree that represents a state, decision point, or piece of information. Nodes connect through parent–child relationships; edges represent possible actions or transitions. The root starts the tree, while leaf nodes mark outcomes where a decision process ends, at least temporarily. section 7.1

Vehicle route planning

A depot is the root node. Child nodes represent route choices, and further nodes represent delivery-order choices. Leaf nodes show complete delivery plans and their costs. section 7.1

Figure 7.1 Tree data structure in vehicle route planning problem

See the branching route-planning tree from vehicle choices to delivery outcomes. section 7.1

How Applied Reinforcement Learning covers it

How deep it goes
Defines nodes, roots, leaves, parent–child links, and edges, and characterizes trees as directed acyclic graphs.
Examples
Uses a delivery plan branching from a depot through route and customer-order choices to costed outcomes.
What you can do after
Evaluate branching plans by simulating alternatives and comparing their outcomes.
How it connects
Connects tree data structures with graphs, states, actions, and transitions.

Also explained in

Compare how 2 books explain node →

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.