Sökning: "Double Deep Q-Network"
Visar resultat 1 - 5 av 8 uppsatser innehållade orden Double Deep Q-Network.
1. Creating an AI opponent withsuper-human performance for Splendor
Uppsats för yrkesexamina på avancerad nivå, Örebro universitet/Institutionen för naturvetenskap och teknikSammanfattning : This project is in collaboration with Piktiv AB. The purpose of the project is tocreate a reinforcement learning agent capable of reaching super human performancein the board game Splendor.Three agents was implemented using a Double Deep Q-Network and certain improvements to the architecture. LÄS MER
2. Offline Reinforcement Learning for Optimization of Therapy Towards a Clinical Endpoint
Master-uppsats, KTH/Medicinteknik och hälsosystemSammanfattning : The improvement of data acquisition and computer heavy methods in recentyears has paved the way for completely digital healthcare solutions. Digitaltherapeutics (DTx) are such solutions and are often provided as mobileapplications that must undergo clinical trials. LÄS MER
3. Board Game AI Using Reinforcement Learning
Uppsats för yrkesexamina på grundnivå, Örebro universitet/Institutionen för naturvetenskap och teknikSammanfattning : The purpose of this thesis is to develop an agent that learns to play an interpretation ofthe popular game Ticket To Ride. This project is done in collaboration with Piktiv AB.This thesis presents how an agent based on the Double Deep Q-network algorithm learnsto play a version of Ticket To Ride using self-play. LÄS MER
4. Research on Dynamic Offloading Strategy of Satellite Edge Computing Based on Deep Reinforcement Learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Nowadays more and more data is generated at the edge of the network, and people are beginning to consider decentralizing computing tasks to the edge of the network. The network architecture of edge computing is different from the traditional network architecture. LÄS MER
5. Deep reinforcement learning for real-time power grid topology optimization
Kandidat-uppsats, Lunds universitet/Matematisk statistikSammanfattning : In our pursuit of carbon neutrality, drastic changes to generation and consumption of electricity will cause new and complex demands on the power grid and its operators. A cheap, promising, and under-exploited mitigation is real-time power grid topology optimization (RTTO). LÄS MER