liveBook · Manning

Packed volume

As explained in Applied Reinforcement Learning

Packed volume is the total three-dimensional volume of items successfully placed in containers.

Packed volume is the combined three-dimensional volume of items successfully placed in containers. It serves as a measure of space utilization: a higher total means less wasted space and greater efficiency. section 3.4

In trailer packing, only successfully placed items contribute to the measure. The environment also rewards each successful placement by the item's volume, aligning this reward with the space-utilization KPI. section 3.4

Figure 3.7 Visualization of one instance of trailer loading and packing environment.

See how a random policy distributes items across trailers of different shapes. section 3.4

How Applied Reinforcement Learning covers it

How deep it goes
Defines the KPI and links it to item-level rewards for successful placements.
Examples
Illustrates packing 12 items into four differently shaped trailers with a random policy.
What you can do after
Evaluate space use by comparing the total volume of items successfully packed.
How it connects
Connects space utilization with placement success and volume-based rewards.

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.