Super Mario Bros RL

Alt text

1. Setup

Requirements


2. How to Train

Modify the parameters in mario_a2c.py as you like.

python3 mario_a2c.py

or

python3 mario_ppo.py

3. How to Eval

Modify the is_load_model, is_render parameters in mario_a2c.py as you like.

python3 mario_a2c.py

or

python3 mario_ppo.py

4. Loss/Reward Graph

It use just A2C(PAAC) image


It use just ICM and no ext reward.(Curiosity-driven) image

References

[1] Actor-Critic Algorithms
[2] Efficient Parallel Methods for Deep Reinforcement Learning
[3] Noisy Networks for Exploration
[4] Proximal Policy Optimization Algorithms
[5] Curiosity-driven Exploration by Self-supervised Prediction

Mario_rl

Mario_rl Info

⭐ Stars 59
🔗 Source Code github.com
🕒 Last Update 2 months ago
🕒 Created 3 years ago
🐞 Open Issues 9
➗ Star-Issue Ratio 7
😎 Author jcwleo