Playing Flappy Bird with DRL

This repository contains our term project in the Reinforcement Learning course in PUCRS.

Environment

The environment used in this project is an implementation of the Flappy Bird game using the OpenAI Gym library.

We are using the version FlappyBird-v0 yields simple numerical information about the game's state as observations. The yielded attributes are the:

• horizontal distance to the next pipe;
• difference between the player's y position and the next hole's y position.

         

See more in Talendar/flappy-bird-gym: An OpenAI Gym environment for the Flappy Bird game

RL Algorithms

• Deep Q-Network (DQN)
• Proximal Policy Optimization (PPO)

Changelog

See the GitHub Tags for a history of notable changes to this project.

License

This software is licensed under the Apache 2.0 LICENSE.