This is a private project to make Super Mario Agent.

It consists of training an agent to clear Super Mario Bros with deep reinforcement learning methods.

Here are my super mario agents with dueling network. ( trained 7,000 epoch )

(25-05-20) SuperMario with PPO has been updated!

git clone https://github.com/jiseongHAN/Super-Mario-RL.git
cd Super-Mario-RL

pip install -r requirements.txt

• Install openAI gym

pip install 'gym'

• Install Pytorch

pip install torch torchvision

• Install nes-py

pip install nes-py

• Install gym-super-mario-bros

pip install gym-super-mario-bros

• Train with dueling dqn.

python duel_dqn.py

• Train with PPO.

python ppo.py

• score.p : save total score every 50 episode
• *.pth : save weight of q, q_target every 50 training

• (Now, pre-trained agent has been corrupted😢)
• Test and render trained agent.
• To test our agent, we need 'q_target.pth' that generated at the training step.
• (eval.py with PPO is not supported now)

python eval.py

• Or you can use your own agent.

python eval.py your_own_agent.pth

Wang, Ziyu, et al. "Dueling network architectures for deep reinforcement learning." International conference on machine learning. PMLR, 2016.

Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017).