- Created a tabular reinforcement learning environment.
- Applied Q-learning in the environment created.
- Applied Soft Actor Critic to Atari MsPacman.
- Applied Deep Q-Network to Atari MsPacman.
Python Version: 3.8.3
Main Packages used:
- opencv-python==4.5.1.48
- torch==1.8.1
- torchvision==0.9.1
Requirements:
<pip install -r requirements.txt>
The original data was from OpenAI Gym.
Best game by SAC:
Pacman gets stuck in a corner and stops moving.
Best game by DQN:
Pacman moves more smoothly and does not stop moving.
- DQN outperforms SAC in Atari MsPacman, which suggests that DQN performs better than SAC when the environment has complex rules and uncertainty.
All jupyter notebooks are available as ipynb.
- Task_1: Create a tabular reinforcement learning environment
- Task_2: Apply Q-learning to the environment created in Task_1
- Task_3: Apply SAC to Atari MsPacman
- Task_4: Apply DQN to Atari MsPacman
- Code: Contains all of the codes implemented
- Report: The report for the whole project