Sökning: "Reward Function"

Visar resultat 11 - 15 av 85 uppsatser innehållade orden Reward Function.

1. 11. Är belöning och ökad tolerans i missbruksvården ett vinnande koncept? : En kvalitativ intervjustudie av behandlares upplevelse kring belöning som arbetsmetod samt hur en mer tolerant syn på droganvändningsproblematik kan främja behandlingsprocessen och minska stigmatisering kring droganvändning

   Uppsats för yrkesexamina på grundnivå, Högskolan Dalarna/Institutionen för hälsa och välfärd

   Författare :Hanna Angantyr; Oskar Nilsson; [2023]
   Nyckelord :Adolescent; Drug use; Stigmatization; reward; criminalization; Ungdomar; Droganvändning; Stigmatisering; belöning; kriminalisering;

   Sammanfattning : The purpose of this study was to examine drug counselors' experience of using reward as a work method and how a more lenient view on substance use can help foster the treatment process and reduce stigma surrounding drug use. The study is based on semi-structured interviews with 4 drug counselors from a municipality in Sweden. LÄS MER

3. 12. A Generic Model of Motivation in Artificial Animals Based on Reinforcement Learning

   Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

   Författare :Birger Kleve; Pietro Ferrari; [2022-05-06]
   Nyckelord :reinforcement; learning; reward; shaping; animat; homeostasis; ecosystem; motivation;

   Sammanfattning : This thesis is a part of a broader research project at Chalmers University of Technology focused on ecosystems’ simulations using reinforcement learning artificial animals, called animats. The scope of this project is to provide animats with a reward signal which should ultimately drive animats’ learning towards adaptation of their environment. LÄS MER

4. 13. Self-Play Reinforcement Learning for Finding Intrusion Prevention Strategies

   Master-uppsats, KTH/Matematisk statistik

   Författare :Jakob Stymne; [2022]
   Nyckelord :Network security; automation; reinforcement learning; Markov Security Games; Neural Fictitious Self Play; Nätverkssäkerhet; automatisering; förstärkningsinlärning; Markovianska säkerhetsspel; Neural Fictitious Self Play;

   Sammanfattning : This Master thesis studies automated intrusion prevention using self-play reinforcement learning. We extend a decision-theoretic model of the intrusion prevention use case based on optimal stopping theory proposed in previous work to a game-theoretic setting. LÄS MER

5. 14. Carrots, Sticks, and Other Tricks: Understanding the effectiveness and robustness of social mechanisms for encouraging cooperation in a complex adaptive system

   D-uppsats, Handelshögskolan i Stockholm/Institutionen för nationalekonomi

   Författare :Thomas Atherton; Andreas Bergström; [2022]
   Nyckelord :Agent-based modelling; Behavioural; Complexity; Cooperation; Evolutionary;

   Sammanfattning : Cooperation is critical for success in many economic interactions, but social dilemmas between the best outcomes for society and for individual decision-makers often arise. This thesis adds to existing game-theoretic and behavioural studies by evaluating cooperation in the public goods game (a canonical social dilemma) in a more complex, realistic system. LÄS MER

7. 15. Towards Anatomically Plausible Streamline Tractography with Deep Reinforcement Learning

   Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

   Författare :Erika Bengtsdotter; [2022]
   Nyckelord :Deep Reinforcement Learning; Plausible; Track-To-Learn; Tractography;

   Sammanfattning : Tractography is a tool that is often used to study structural brain connectivity from diffusion magnetic resonance imaging data. Despite its ability to visualize fibers in the white brain matter, it results in a high number of invalid streamlines. LÄS MER