Fig 1 - available via license: Creative Commons Attribution-NonCommercial 4.0 International
Content may be subject to copyright.
![Screen capture of flappy bird [1]](publication/366661079/figure/fig1/AS:11431281110460116@1672573842969/Screen-capture-of-flappy-bird-1.png)
Source publication
![Fig. 1. Screen capture of flappy bird [1]](publication/366661079/figure/fig1/AS:11431281110460116@1672573842969/Screen-capture-of-flappy-bird-1_Q320.jpg)
![Fig. 2. Reinforcement learning process [5]](publication/366661079/figure/fig2/AS:11431281110466455@1672573843020/Reinforcement-learning-process-5_Q320.jpg)
Context in source publication
Context 1
... if players do nothing, the bird will fall down a bit because of gravity. Players' goal is to control the bird to stay alive and move forward as far as they could. Every time players successfully fly through one pipe one score will be added on the scoreboard. This game can be played in http://flappybird.io and the game screen capture shows it in Fig. 1. Due to the fact that the agent can only do 2 actions and whether game over or not is easy to conclude, flappy bird could be a fundamental research about training artificial intelligence to play video game by deep reinforcement learning. ...
Similar publications
In this paper, reinforcement learning will be applied to the game flappy bird with two methods DQN and Q-learning. Then, we compare the performance through the visualization of data. Furthermore, more results from other games are summarized to analysis the corresponding advantages and disadvantages. Finally, we discuss and compare these two reinfor...
This paper studies how a domain-independent planner and combinatorial search can be employed to play Angry Birds, a well established AI challenge problem. To model the game, we use PDDL+, a planning language for mixed discrete/continuous domains that supports durative processes and exogenous events. The paper describes the model and identifies key...
Citations
A transformer neural network is employed in the present study to predict Q-values in a simulated environment using reinforcement learning techniques. The goal is to teach an agent to navigate and excel in the Flappy Bird game, which became a popular model for control in machine learning approaches. Unlike most top existing approaches that use the game’s rendered image as input, our main contribution lies in using sensory input from LIDAR, which is represented by the ray casting method. Specifically, we focus on understanding the temporal context of measurements from a ray casting perspective and optimizing potentially risky behavior by considering the degree of the approach to objects identified as obstacles. The agent learned to use the measurements from ray casting to avoid collisions with obstacles. Our model substantially outperforms related approaches. Going forward, we aim to apply this approach in real-world scenarios.
