Machine Learning in StarCraft II - Lowering the Difficulty Threshold of Starting From Scratch
dc.contributor.author | BENNHAGE, SVANTE | |
dc.contributor.author | GULDBRAND, ERIC | |
dc.contributor.author | OUEIDAT, OMAR | |
dc.contributor.author | TORSTENSSON, MATTIAS | |
dc.contributor.author | ULANDER, SILAS | |
dc.contributor.author | WALLHEDE, ERIK | |
dc.contributor.department | Chalmers tekniska högskola / Institutionen för data och informationsteknik | sv |
dc.contributor.examiner | Ahrendt, Wolfgang | |
dc.contributor.examiner | Fjeld, Morten | |
dc.contributor.examiner | Knutsson, Sven | |
dc.contributor.supervisor | Duregård, Jonas | |
dc.date.accessioned | 2020-10-19T14:06:33Z | |
dc.date.available | 2020-10-19T14:06:33Z | |
dc.date.issued | 2019 | sv |
dc.date.submitted | 2020 | |
dc.description.abstract | Artificial intelligence research is currently a hot topic within many industries. In terms of research, games such as StarCraft II provide a good testing ground due to its accessibility. However, getting started can still be more difficult than it should be. This paper aims to facilitate the development of a machine learning agent for StarCraft II by designing tools for data collection, making a simple API built on top of PySC2 to facilitate interaction with the game and by analyzing a few different types of artificial neural networks with respect to StarCraft II. It is concluded that defining reward functions for reinforcement learning can give rise to unexpected behaviors. A further conclusion is that convolutional neural networks tend to be more resource intensive than non-convolutional networks and that they are thus less suited for anyone without access to large computational power. Lastly, a network is trained on collected data to continuously predict the win chance for players in a StarCraft II match. Unfortunately the network does not become successful in its task, likely in part due to the simplicity of the network. | sv |
dc.identifier.coursecode | DATX02 | sv |
dc.identifier.uri | https://hdl.handle.net/20.500.12380/301903 | |
dc.language.iso | eng | sv |
dc.setspec.uppsok | Technology | |
dc.subject | Artificial Neural Networks | sv |
dc.subject | Machine Learning | sv |
dc.subject | StarCraft II | sv |
dc.subject | Reinforcement learning | sv |
dc.subject | Supervised learning | sv |
dc.title | Machine Learning in StarCraft II - Lowering the Difficulty Threshold of Starting From Scratch | sv |
dc.type.degree | Examensarbete på kandidatnivå | sv |
dc.type.uppsok | M2 |