Sökning: "Reward Function"

Visar resultat 6 - 10 av 85 uppsatser innehållade orden Reward Function.

1. 6. Scalable Reinforcement Learning for Formation Control with Collision Avoidance : Localized policy gradient algorithm with continuous state and action space

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

   Författare :Andreu Matoses Gimenez; [2023]
   Nyckelord :Control theory; Multi-agent systems; Distributed systems; Formation control; Collision avoidance; Reinforcement learning; Teoria de control; Sistemes multiagent; Sistemes distribuïts; Control de formació; Prevenció de col·lisions; Reinforcement Learning; Reglerteknik; Multi-agent system; Distribuerade system; formationskontroll; Kollisionsundvikande; Reinforcement learning; Teoría de control; Sistemas multiagente; Sistemas distribuidos; Control de formación; Prevención de colisiones; Reinforcement Learning;

   Sammanfattning : In the last decades, significant theoretical advances have been made on the field of distributed mulit-agent control theory. One of the most common systems that can be modelled as multi-agent systems are the so called formation control problems, in which a network of mobile agents is controlled to move towards a desired final formation. LÄS MER

3. 7. Random Edge is not faster than Random Facet on Linear Programs

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Nicole Hedblom; [2023]
   Nyckelord :Simplex method; simplex; Random Edge; Linear Programming; Random Facet; randomized pivoting rule; Markov decision process; Simplexmetoden; Random Edge; linjärprogrammering; Random Facet; Markov-beslutsprocess;

   Sammanfattning : A Linear Program is a problem where the goal is to maximize a linear function subject to a set of linear inequalities. Geometrically, this can be rephrased as finding the highest point on a polyhedron. The Simplex method is a commonly used algorithm to solve Linear Programs. LÄS MER

4. 8. Multi-Agent Information Gathering Using Stackelberg Games

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

   Författare :Yiming Hu; [2023]
   Nyckelord :Information gathering; Autonomous exploration; Multi-agent coordination; Multi-agent system; Informationsinsamling; Autonom utforskning; Samordning av flera agenter; multiagentsystem;

   Sammanfattning : Multi-agent information gathering (MA-IG) enables autonomous robots to cooperatively collect information in an unfamiliar area. In some scenarios, the focus is on gathering the true mapping of a physical quantity such as temperature or magnetic field. LÄS MER

5. 9. The influence of favouritism as non financial incentives on employee performance

   Magister-uppsats, Umeå universitet/Handelshögskolan vid Umeå universitet (USBE)

   Författare :Egwuonwu John Rotanna; [2023]
   Nyckelord :;

   Sammanfattning : ABSTRACT In the business sector, favouritism is a frequent and typically disapproved behaviour. However, when used as a reward for excellent employee performance, favouritism can incentivize increased employee productivity and performance. LÄS MER

7. 10. Intelligent autoscaling in Kubernetes : the impact of container performance indicators in model-free DRL methods

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

   Författare :Tommaso Praturlon; [2023]
   Nyckelord :Cloud computing; container autoscaling; resource optimisation; Deep Reinforcement Learning; Actor-Critic; Kubernetes; service mesh; Cloud computing; container autoscaling; Optimering av resurser; Deep Reinforcement Learning; Actor-Critic; Kubernetes; service mesh;

   Sammanfattning : A key challenge in the field of cloud computing is to automatically scale software containers in a way that accurately matches the demand for the services they run. To manage such components, container orchestrator tools such as Kubernetes are employed, and in the past few years, researchers have attempted to optimise its autoscaling mechanism with different approaches. LÄS MER