Watch Our Agent Learn

Author(s): Rem E

Originally published on Towards AI.

Tutorial 7: Implementing Dynamic Programming for our maze problem

Not a Medium member yet? No worries, you can still read it here!

This article discusses the implementation of a Dynamic Programming (DP) algorithm to help an agent successfully navigate a maze problem. It elaborates on the project setup, explaining how to gather the necessary code from a GitHub repository and follow the same structure as previous tutorials. Furthermore, it dives into how the agent class is implemented, detailing the processes for calculating the value of states and updating policies based on the values determined. Additionally, it outlines the differences between deterministic and stochastic policies, and emphasizes the importance of understanding dynamic programming’s role in reinforcement learning. Finally, the tutorial culminates in a demonstration of the agent’s ability to reach its goal autonomously.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI