Sökning: "Djup Förstärkning Lärande"

Hittade 4 uppsatser innehållade orden Djup Förstärkning Lärande.

1. 1. Link Adaptation in 5G Networks : Reinforcement Learning Framework based Approach

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Siva Satya Sri Ganesh Seeram; [2022]
   Nyckelord :Link Adaptation; OLLA; AMC; Reinforcement Learning; DDPG; BLER; Länkanpassning; OLLA; AMC; förstärkningsinlärning; DDPG; BLER;

   Sammanfattning : Link Adaptation is a core feature introduced in gNodeB (gNB) for Adaptive Modulation and Coding (AMC) scheme in new generation cellular networks. The main purpose of this is to correct the estimated Signal-to-Interference-plus-Noise ratio (SINR) at gNB and select the appropriate Modulation and Coding Scheme (MCS) so the User Equipment (UE) can decode the data successfully. LÄS MER

3. 2. Automatic game-testing with personality : Multi-task reinforcement learning for automatic game-testing

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Oleguer Canal Anton; [2021]
   Nyckelord :Deep Reinforcement Learning; Multi-Task; Successor Features; Game- Testing; Personas; Djup förstärkningsinlärning; Multitasking; Efterföljande kännetecken; Speltestning; Artificiell intelligens; Persona.;

   Sammanfattning : This work presents a scalable solution to automate game-testing. Traditionally, game-testing has been performed by either human players or scripted Artificial Intelligence (AI) agents. While the first produces the most reliable results, the process of organizing testing sessions is time consuming. LÄS MER

4. 3. Research on Dynamic Offloading Strategy of Satellite Edge Computing Based on Deep Reinforcement Learning

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Rui Geng; [2021]
   Nyckelord :Deep reinforcement learning; Satellite edge computing; Offloading strategy; Djup Förstärkning Lärande; Satellit Kant Datoranvändning; Avlastning Strategi;

   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. 4. A comparison of genetic algorithm and reinforcement learning for autonomous driving

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ziyi Xiang; [2019]
   Nyckelord :Thesis; Machine learning; Genetic algorithm; Deep reinforcement learning; Autonomous driving; Thesis; Maskininlärning; Genetisk algoritm; Djup förstärkning lärande; självkörandebilar;

   Sammanfattning : This paper compares two different methods, reinforcement learning and genetic algorithm for designing autonomous cars’ control system in a dynamic environment. The research problem could be formulated as such: How is the learning efficiency compared between reinforcement learning and genetic algorithm on autonomous navigation through a dynamic environment? In conclusion, the genetic algorithm outperforms the reinforcement learning on mean learning time, despite the fact that the prior shows a large variance, i. LÄS MER