Super Reinforcement Bros: Playing Super Mario Bros with Reinforcement Learning

2020-12-14 · CUHK Course IERG5350 2020 12 · Nan Zhang, Zixing Song

We plan to apply and adjust some well-known reinforcement learning (RL) algorithms to train an automatic agent to play the 1985 Nintendo game Super Mario Bros under a speedrun rule. The agent may learn several control policies from raw pixel data by using deep reinforcement learning. By the end of the project, we expect the model to perform comparably to or top human players in a given stage. Code and pre-trained models are available at https://github.com/AnthonySong98/Super-Mario-Bros-PPO. The video recording is available at https://drive.google.com/file/d/1A9d81LUKM9h8Msw9l9Xu2PrpCXnZGgcl/view.

📄 PDF Abstract BibTeX

Code (1)

anthonysong98/super-mario-bros-ppo 공식 구현 pytorch

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

RAMario: Experimental Approach to Reptile Algorithm -- Reinforcement Learning for Mario

2023-05-16 · Sanyam Jain

This research paper presents an experimental approach to using the Reptile algorithm for reinforcement learning to train a neural network to play Super Mario Bros. We implement the Reptile algorithm using the Super Mario…

Few-Shot Learning Meta-Learning reinforcement-learning Reinforcement Learning

Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study

2021-06-30 · Tianye Shu, Jialin Liu, Georgios N. Yannakakis

We introduce a procedural content generation (PCG) framework at the intersections of experience-driven PCG and PCG via reinforcement learning, named ED(PCG)RL, EDRL in short. EDRL is able to teach RL designers to generat…

Diversity reinforcement-learning Reinforcement Learning (RL)

Improving Deep Localized Level Analysis: How Game Logs Can Help

2022-12-07 · Natalie Bombardieri, Matthew Guzdial

Player modelling is the field of study associated with understanding players. One pursuit in this field is affect prediction: the ability to predict how a game will make a player feel. We present novel improvements to af…

Optimizing Mario Adventures in a Constrained Environment

2023-12-14 · Sanyam Jain

This project proposes and compares a new way to optimise Super Mario Bros. (SMB) environment where the control is in hand of two approaches, namely, Genetic Algorithm (MarioGA) and NeuroEvolution (MarioNE). Not only we l…

Domain Adaptation Transfer Learning

Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1

2026-06-28 · Jesse Ponnock, Lucas Ho arxiv

World 1-1 of Super Mario Bros is widely celebrated as a masterclass in game design: its progressive structure is credited with teaching players core mechanics through the level itself. We ask whether that structure is em…

Reinforcement Learning