Super-Mario-Bros-RL

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

Super-Mario-Bros-RL

(★ 82)

This project explores deep reinforcement learning, hybrid actor-critic approach with A3C/PPO combined with curiosity for playing Super Mario Bros

Super-Mario-Bros-RL 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Deep Reinforcement Learning : A3C | PPO | Curiosity applied to Super Mario Bros.

This is the final project for the Reinforcement Learning course at the MVA Masters 2018/2019.

The project was done by [Amine Sadeq](https://github.com/sadeqa) & [Otmane Sakhi](https://github.com/otmhi), You can check the final project paper : ["Exploring Deep Reinforcement Learning with Super Mario Bros"] in this repository.

It explores A3C and PPO algorithms and combine them with an intrinsic reward based on curiosity.

![](https://raw.githubusercontent.com/sadeqa/Super-Mario-Bros-RL/master/A3C/video/mario.gif)

### A3C curiosity vs no curiosity in Dense reward

![dense_cur](https://raw.githubusercontent.com/sadeqa/Super-Mario-Bros-RL/master/figures/dense_plot.png)

### A3C curiosity vs no curiosity in Sparse reward

![sparse_cur](https://raw.githubusercontent.com/sadeqa/Super-Mario-Bros-RL/master/figures/sparse_plot.png)

### A3C curiosity vs PPO curiosity in Dense reward

![dense_ppo](https://raw.githubusercontent.com/sadeqa/Super-Mario-Bros-RL/master/figures/dense_ppo_plot.png)

### A3C curiosity vs PPO curiosity in Sparse reward

![sparse_ppo](https://raw.githubusercontent.com/sadeqa/Super-Mario-Bros-RL/master/figures/sparse_ppo_plot.png)

Super-Mario-Bros-RL

Super-Mario-Bros-RL 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Super-Mario-Bros-RL

Super-Mario-Bros-RL 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README