Improved Version of the Pong Game Using RL TD3

Version 1.0.4 (2,04 MB) von Ismael Abdulrahman
An improved version of the pong game.
0.0
(0)
76 Downloads
Aktualisiert 7. Nov 2021

Lizenz anzeigen

This program uses the TD3 RL technique to train an agnet for the pong game.
It is the same as the original one developed by Johanna Pingel (a MATLAB staff and blogger) with the following changes:
1. Another state is added to the observation-state vector called q8 with the equation: q8 = abs(ball_x-paddle_x)
2. TD3 is used instead of DDPG
3. rng is added to use the same random noise at each time the agent is trained (for comparison)
Original code:
https://blogs.mathworks.com/deep-learning/2021/03/12/playing-pong-using-reinforcement-learning/

Zitieren als

Ismael Abdulrahman (2024). Improved Version of the Pong Game Using RL TD3 (https://www.mathworks.com/matlabcentral/fileexchange/101629-improved-version-of-the-pong-game-using-rl-td3), MATLAB Central File Exchange. Abgerufen .

Kompatibilität der MATLAB-Version
Erstellt mit R2021b
Kompatibel mit R2021a bis R2021b
Plattform-Kompatibilität
Windows macOS Linux

Community Treasure Hunt

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

Start Hunting!

MATLAB_Agent

My_Agent

Version Veröffentlicht Versionshinweise
1.0.4

Fixing typos.

1.0.3

Minor change.
1.0.2

Minor change.
1.0.1

Minor change.
1.0.0