https://github.com/codewithcharan/ai-mario

https://github.com/codewithcharan/ai-mario

Last synced: 8 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/codewithcharan/ai-mario
• Owner: CodeWithCharan
• Created: 2023-11-12T19:06:21.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-05-21T11:32:26.000Z (about 2 years ago)
• Last Synced: 2025-04-03T03:42:46.932Z (about 1 year ago)
• Language: Jupyter Notebook
• Size: 36 MB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# A REINFORCEMENT LEARNING APPROACH FOR PLAYING SUPER MARIO BROS

Super Mario Bros. game, which was released in 1985 for the Nintendo Entertainment System, had 32 levels spanning across 8 worlds. The Mario Agent successfully cleared 6 levels from these 8 worlds. 

## Requirements

| Module               | Version |

|----------------------|---------|

| gym                  | 0.21.0  |

| gym-super-mario-bros | 7.3.0   |

| nes-py               | 8.2.1   |

| pyglet               | 1.5.21  |

| stable-baselines3    | 1.8.0   |

| torch                | 2.1.0+cu118  |

## Results

| stage | gameplay | status |

|:-:|:-:|:-:|

| 1-1 | ![Mario_AI_1_1](https://github.com/CodeWithCharan/AI-Mario/assets/106027109/53318c40-f2da-4ed6-b706-a62a609af267) | clear |

| 2-1 | ![Mario_AI_2_1](https://github.com/CodeWithCharan/AI-Mario/assets/106027109/70a84ae4-19ad-40a4-adf7-70531f34cae1) | clear |

| 3-2 | ![Mario_AI_3_2](https://github.com/CodeWithCharan/AI-Mario/assets/106027109/16bbe93e-9751-4ac0-921a-6e65237371c0) | clear |

| 5-1 | ![Mario_AI_5_1](https://github.com/CodeWithCharan/AI-Mario/assets/106027109/3ff1a035-fe05-44b2-a745-0b64c793d7b9) | clear |

| 6-1 | ![Mario_AI_6_1](https://github.com/CodeWithCharan/AI-Mario/assets/106027109/a0070fa8-a4ea-4377-8076-0d9cb740ec27) | clear |

| 8-2 | ![Mario_AI_8_2](https://github.com/CodeWithCharan/AI-Mario/assets/106027109/5ad51188-d028-4e9e-a082-b3a9a63322c7) | clear |

REFERENCES:

https://github.com/openai/baselines/blob/master/baselines/common/retro_wrappers.py

https://github.com/nicknochnack/MarioRL

https://stable-baselines3.readthedocs.io/en/master/_modules/stable_baselines3/common/atari_wrappers.html

https://youtu.be/dWmJ5CXSKdw?si=CBPaVoSZM665WRwy