Flapai Bird: Training An Agent To Play Flappy Bird Using Reinforcement Learning Techniques

Abstract

Reinforcement learning is one of the most popular approaches for automated game playing. This method allows an agent to estimate the expected utility of its state in order to make optimal actions in an unknown environment. We seek to apply reinforcement learning algorithms to the game Flappy Bird. We implement SARSA and Q-Learning with some modifications such as \(\epsilon\)-greedy policy, discretization and backward updates. We find that SARSA and Q-Learning outperform the baseline, regularly achieving scores of 1400+, with the highest in-game score of 2069.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyvu2020flapai

Related papers

• Angrier Birds: Bayesian Reinforcement Learning (2016)0.00
• Reinforcement Learning Approach For Real Time Strategy Games Battle City And S3 (2016)0.00
• Agile Flight Emerges From Multi-agent Competitive Racing (2025)0.00
• Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay (2016)0.00
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00
• Learning From Learners: Adapting Reinforcement Learning Agents To Be Competitive In A Card Game (2020)0.00
• Reinforcement Learning And Video Games (2019)0.00
• Reinforcement Learning For Constraint Satisfaction Game Agents (15-puzzle, Minesweeper, 2048, And Sudoku) (2021)0.00