Maze Solver——Q-Learning and SARSA algorithm

Versión 1.0.0 (395 KB) por chun chi
In this project, we simulate two agent by Q-Learning and SARSA algorithm and put them in interactive maze environment to train best strategy
186 descargas
Actualizado 23 Oct 2020

Ver licencia

In this project, we simulated the interactive maze environment in the MATLAB real-time editor environment, and implemented two classical Rl (reinforcement learning) algorithms - Q-learning and sarsa algorithm. By creating an agent to move interactively in the maze, two algorithms are used to train the highest incentive value reward and the best maze walking method. Finally, we compare the performance of the two algorithms.

Citar como

chun chi (2024). Maze Solver——Q-Learning and SARSA algorithm (https://www.mathworks.com/matlabcentral/fileexchange/81643-maze-solver-q-learning-and-sarsa-algorithm), MATLAB Central File Exchange. Recuperado .

Compatibilidad con la versión de MATLAB
Se creó con R2020a
Compatible con cualquier versión
Compatibilidad con las plataformas
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Versión Publicado Notas de la versión
1.0.0