A Deep Reinforcement Learning Approach for Pathfinding in Computer Games

One of the biggest challenges of game development is to produce a pathfinding algorithm that bothproduces satisfactory realistic movement results and can solve different scenarios in worlds created by gamedevelopers' unlimited imagination. Furthermore, since the games are programs for the end user, it is desired thatthe systems they contain use as little computer resources as possible and be developed as quickly as possible interms of cost. With the advances in software, lightweight methods have been developed that can provide generalmap coverage in this regard. Although existing solutions can produce strong answers to the problem, they alsocontain some chronic problems that take a long development time to solve. Existing solutions work very well onmaps that are continuous and can be navigated by moving from start to finish. However, it cannot find a solutionin cases where various obstacles must be overcome by various movement mechanics such as jumping, flying ordash are used other than walking. Developers must manually assign links to meshes, significantly prolonging thegame development process on the maps with such features. At the same time, since the connected links areestablished manually, the movement of the object moving on the link does not seem natural. The focus of thisstudy is to create a system that will generate a node network by using artificial neural networks and deepreinforcement learning to overcome the difficulties of existing pathfinding algorithms. Finally, a system that isfast and uses less resources is aimed for the end user, since artificial neural networks will not be used during thebuild phase. Some promising results have been obtained so far, which shows that the alternative methodologyproposed in this study could be a useful alternative for game developers.