English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Usually, there are a lot of monsters in online games. High IQ monsters will increase the playability of the game. This paper presents a tracking algorithm based on neural network, so that the monster can continue to learn and progress. The monster can track the game player through an optimized route and avoid other monsters or obstacles. Introduction Most popular online games are MMRPGs (massively multiplayer online role playing game). In these games, players play various roles. There will be many monsters in the game. If the monster is smarter, it is possible to track the player intelligently and evolve to learn, which will increase the player's interest and increase the playability of the game. In the practical application, the common traversal algorithm can achieve the tracking and avoidance behavior. However, this algorithm has a large amount of computation and consumes more CPU resources. Therefore, a tracking algorithm based on neural network is proposed. The implementation of this algorithm: when the monster appears randomly, the system allocates the original motion path. When the monster finds the player, it calculates the initial path based on the player's position and the obstacles. Then, according to track the player's efficiency and the number of collisions with obstacles, the monster will train their own neural network. At the same time, the genetic algorithm is used to optimize the structure of neural network. Design of the Neural Network. The feed forward neural network is adopted in the algorithm. The network includes input layer, hidden layer and output layer. The neural network takes the current coordinates of the monster and the player's target position as the original input. The neural network takes the motion direction of the monster as output. The sigmoid function is used as the excitation function, and the genetic algorithm is used to learn and upgrade. In this algorithm, the number of cells in the hidden layer is set to 10. Figure 1. The setting of detectors In the game, the environment around the monster always changes. Game engines need to train the ability of the monster to recognize the environment, so that they can judge their own path. When the environment has changed, the monster can automatically change the path. To implement this feature, you need to set detectors in the monster object, as shown in Fig. 1. monster obstacle

A Tracking Algorithm in Game Based on Neural Network