liveBook · Manning

Inventory constraint

As explained in Applied Reinforcement Learning

An inventory constraint limits sales or actions to the finite quantity of products currently available.

An inventory constraint limits sales to the finite stock on hand. In dynamic pricing, the agent must balance earning more per item against selling through its stock within a fixed window. section 3.3

A food truck’s daily stock

A truck starts with 100 tacos and cannot sell more than it has. In the pricing environment, sales each period are capped by current inventory. section 3.3

Table 3.2 Elements of Markov decision process for perishable dynamic pricing
Markov decision process elements
Definitions
State
How many sales periods are left.
How many items are left to sell.
Action
The agent chooses a price from a predefined list, e.g., [8, 10, 12, 15, 18].
Reward
Calculated as the revenue from sales in that period.
Penalty if items remain unsold after the last period.
Transition Dynamics
Demand drops as the price increases (price sensitivity).
Demand slightly increases over time due to urgency (people rush to buy near the end).
Random noise is added to simulate uncertainty.

See how remaining inventory appears in the state alongside time left, pricing actions, rewards, and demand dynamics. section 3.3

How Applied Reinforcement Learning covers it

How deep it goes
Defines finite starting stock and caps sales at available inventory, without developing a broader theory of constraints.
Examples
Uses a food truck with 100 tacos and a perishable-product pricing environment.
What you can do after
Build a dynamic-pricing environment that caps each period’s sales at available stock.
How it connects
Connects inventory to dynamic pricing, demand, revenue management, and reinforcement learning.

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.