BitsExplorer

BitsExplorer finds what people are building with AI, every day. See today's picks →

Preview of Markdown

Markdown

Three RL agents, one revenue-management problem: bandits, tabular Q-learning, and a DQN learn to price a limited-inventory sale against a deadline - trained offline, played back live client-side (ONNX in-browser inference), validated against an exact dynamic-programming solution

Description excerpted from the original listing, which is linked below.

Open it Source code

The week in AI-built software

Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.

Read the latest week