Computational Model Library

Cliff Walking with Q-Learning NetLogo Extension (version 1.0.0)

This model implements a classic scenario used in Reinforcement Learning problem, the “Cliff Walking Problem”. Consider the gridworld shown below (SUTTON; BARTO, 2018). This is a standard undiscounted, episodic task, with start and goal states, and the usual actions causing movement up, down, right, and left. Reward is -1 on all transitions except those into the region marked “The Cliff.” Stepping into this region incurs a reward of -100 and sends the agent instantly back to the start (SUTTON; BARTO, 2018).

CliffWalking

The problem is solved in this model using the Q-Learning algorithm. The algorithm is implemented with the support of the NetLogo Q-Learning Extension

cliff-walking.png

Release Notes

To use this model you just have to open it with NetLogo 6.1.0. You also should add the Q-Learning Extension to your NetLogo, this can be done through the NetLogo Extension Manager.

Version Submitter First published Last modified Status
1.0.0 Kevin Kons Tue Dec 10 18:48:10 2019 Tue Dec 10 18:48:10 2019 Published

Discussion

Download
This website uses cookies and Google Analytics to help us track user engagement and improve our site. If you'd like to know more information about what data we collect and why, please see our data privacy policy. If you continue to use this site, you consent to our use of cookies.