Sökning: "Starcraft 2"
Visar resultat 1 - 5 av 12 uppsatser innehållade orden Starcraft 2.
1. Evaluating Curiosity Driven Exploration in a Large Action Space using Starcraft 2
Master-uppsats, Lunds universitet/Institutionen för datavetenskapSammanfattning : .... LÄS MER
2. Evaluating behaviour tree integration in the option critic framework in Starcraft 2 mini-games with training restricted by consumer level hardware
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This thesis investigates the performance of the option critic (OC) framework combined with behaviour trees (BTs) in Starcraft 2 mini-games when training time is constrained by a time frame limited by consumer level hardware. We test two such combination models: BTs as macro actions (OCBT) and BTs as options (OCBToptions) and measure the relative performance to the plain OC model through an ablation study. LÄS MER
3. Maskininlärningsmetoder tillämpade på StarCraft 2 - En undersökning av reinforcement och imitation learning
Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Inom artificiell intelligens, som kontinuerligt utvecklas, har maskininlärning tagit en central roll. Medan regelbaserad AI varit tillräcklig för att lösa grundläggande uppgifter behöver dagens utmaningar mer avancerade metoder. LÄS MER
4. Gate Recurrent Unit Neural Networks for Hearing Instruments
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : Gated Recurrent Unit (GRU) neural networks have gained popularity for applications such as keyword spotting, speech recognition and other artificial intelligence applications. Typically for most applications training and inference is performed on cloud servers, and the result are transferred to the power constrained device, e.g. LÄS MER
5. Monto Carlo Tree Search in Real Time Strategy Games with Applications to Starcraft 2
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This thesis presents an architecture for an agent that can play the real-time strategy game Starcraft 2 (SC2) by applying Monte Carlo Tree Search (MCTS) together with genetic algorithms and machine learning methods. Together with the MCTS search, a light-weight and accurate combat simulator for SC2 as well as a build order optimizer are presented as independent modules. LÄS MER