/Enhancing-Q-Learning-with-Neural-Networks-and-Replay-Buffer-for-the-Catch-Game

The project aims to compare the performance of the RL agent with and without these enhancements and analyze the impact of different hyperparameters on learning speed and stability.

Primary LanguageJupyter Notebook

Enhancing-Q-Learning-with-Neural-Networks-and-Replay-Buffer-for-the-Catch-Game

The project aims to compare the performance of the RL agent with and without these enhancements and analyze the impact of different hyperparameters on learning speed and stability.