Reinforcement Learning and Neuroevolution in Flappy Bird Game

Brandão, André; Pires, Pedro; Georgieva, Pétia

doi:10.1007/978-3-030-31332-6_20

Cited by 11 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where x t is the input represented as pixels at t moment, e t is the action taken at the t moment, and hl represents an dynamic array of most recent pixel input that we are keeping tracking of, which is a design that aims to reduce the space used by the unnecessary storage of states from t = 1 until all other consecutive states [3].…”

Section: Modelmentioning

confidence: 99%

Deep Reinforcement Learning for 2D Flappy Brid Game

2022

SHS Web Conf.

View full text Add to dashboard Cite

In recent years, the prevailing of application of Deep Reinforcement Learning have granted the traditional game AI training a brand-new perspective. Google’s Alpha Go agent might mark the beginning of the trend. While many 2D games have been researched for effective trained agent to gain extraordinary performance, Flappy Bird is among, perhaps, the most popular one that could demonstrate the effectiveness of trained AI. This research has successfully trained a efficient agent using Deep-Q network that could outperforms its human counterparts. Although previous trainings have also granted successful results, due to the optimization in the memory array to store previous states, the training time has been largely reduced, which is useful for future agent training optimization.

show abstract

Section: Modelmentioning

confidence: 99%

Deep Reinforcement Learning for 2D Flappy Brid Game

2022

SHS Web Conf.

View full text Add to dashboard Cite

show abstract

“…Neuroevolution and Reinforcement learning algorithms are some of the algorithms that are used to create AI bots or artificial agents. [1], [7] and [8] have implemented a configuration of an ANN called Neuroevolution. The algorithm does not depend on the actions taken by the agents as a whole.…”

Section: Literature Surveymentioning

confidence: 99%

“…The algorithm does not depend on the actions taken by the agents as a whole. [3], [4], [5], [6] and [7] use Reinforcement Learning algorithm with Deep Q-Learning to train the agents. The performance of the Neuroevolution algorithm depends on the objective function, initial population, mutation rate, weights and bias added to the network, the activation function used and overall topology of the network.…”

Section: Literature Surveymentioning

confidence: 99%

“…There are two ways of making use of the environment. Authors in [3], [4], [6] and [7] use DNN to extract the features from the frame of the game and they form the input to the agent. However, [1], [5] and [8] make use of the game itself and place the agent to perceive its surroundings.…”

Section: Literature Surveymentioning

confidence: 99%

“…The CNN is used with preprocessed input image by removing the background, grayscale, and resizing to 80 x 80, 2 CNN layers were used, one using sixteen 5 × 5 kernels with stride 2, and another with thirty-two 5 × 5 kernels with stride 2. [7] proposes the use of specific feature selection and presents the state by the bird velocity and the difference between the bird's position and the next lower pipe. This reduces the feature space and eliminates the need for deeper modules.…”

Section: Literature Surveymentioning

confidence: 99%

See 2 more Smart Citations

Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

Selvan¹,

Game²

2022

Preprint

View full text Add to dashboard Cite

For over a decade now, robotics and the use of artificial agents have become a common thing. Testing the performance of new path finding or search space optimisation algorithms has also become a challenge as they require simulation or an environment to test them. The creation of artificial environments with artificial agents is one of the methods employed to test such algorithms. Games have also become an environment to test them. The performance of the algorithms can be compared by using artificial agents that will behave according to the algorithm in the environment they are put in. The performance parameters can be, how quickly the agent is able to differentiate between rewarding actions and hostile actions. This can be tested by placing the agent in an environment with different types of hurdles and the goal of the agent is to reach the farthest by taking decisions on actions that will lead to avoiding all the obstacles. The environment chosen is a game called "Flappy Bird". The goal of the game is to make the bird fly through a set of pipes of random heights. The bird must go in between these pipes and must not hit the top, the bottom, or the pipes themselves. The actions that the bird can take are either to flap its wings or drop down with gravity. The algorithms that are enforced on the artificial agents are NeuroEvolution of Augmenting Topologies (NEAT) and Reinforcement Learning. The NEAT algorithm takes an 'N' initial population of artificial agents. They follow genetic algorithms by considering an objective function, crossover, mutation, and augmenting topologies. Reinforcement learning, on the other hand, remembers the state, the action taken at that state, and the reward received for the action taken using a single agent and a Deep Q-learning Network. The performance of the NEAT algorithm improves as the initial population of the artificial agents is increased.

show abstract

Parallel Distributed Implementation of Neuroevolution of Augmenting Topologies in Continuous Control Tasks

Achour

Doroshenko

2021

2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT)

View full text Add to dashboard Cite

Reinforcement Learning and Neuroevolution in Flappy Bird Game

Cited by 11 publications

References 7 publications

Deep Reinforcement Learning for 2D Flappy Brid Game

Deep Reinforcement Learning for 2D Flappy Brid Game

Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

Parallel Distributed Implementation of Neuroevolution of Augmenting Topologies in Continuous Control Tasks

Contact Info

Product

Resources

About