Sökning: "Reinforcement learning"

Visar resultat 1 - 5 av 121 uppsatser innehållade orden Reinforcement learning.

  1. 1. Multi Agent Reinforcement Learning

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Rikard Isaksson; [2019-06-13]
    Nyckelord :;

    Sammanfattning : Machine learning and artificial intelligence has been a hot topic the last few years, thanks to improved computational power the machine learning framework can now be applied to larger data sets. Reinforcement learning is a group of machine learning algorithms where one does not know the correct answer in advance, much like unsupervised learning. LÄS MER

  2. 2. When we see something that is well beyond our understanding : The duty of States to investigate war crimes and how it applies to autonomous weapons systems

    Kandidat-uppsats, Försvarshögskolan

    Författare :Conrad Palmcrantz; [2019]
    Nyckelord :lethal autonomous weapons; machine learning; grave breaches; accountability; command responsibility;

    Sammanfattning : This thesis analyses States’ duty to investigate grave breaches of humanitarian law and how it applies to deep reinforcement learning autonomous weapons. It identifies basic technologic intricacies related to deep reinforcement learning and discusses what issues may arise if such software is used in weapons systems. LÄS MER

  3. 3. Using Deep Reinforcement Learning For Adaptive Traffic Control in Four-Way Intersections

    Master-uppsats, Linköpings universitet/Kommunikations- och transportsystemLinköpings universitet/Tekniska fakulteten; Linköpings universitet/Kommunikations- och transportsystemLinköpings universitet/Tekniska fakulteten

    Författare :Gustav Jörneskog; Josef Kandelan; [2019]
    Nyckelord :Deep Reinforcement Learning; Traffic Control System; Green Wave; SUMO;

    Sammanfattning : The consequences of traffic congestion include increased travel time, fuel consumption, and the number of crashes. Studies suggest that most traffic delays are due to nonrecurring traffic congestion. Adaptive traffic control using real-time data is effective in dealing with nonrecurring traffic congestion. LÄS MER

  4. 4. Djupinlärning på Snake

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI); KTH/Skolan för teknikvetenskap (SCI)

    Författare :Anton Finnson; Victor Molnö; [2019]
    Nyckelord :;

    Sammanfattning : Algoritmer baserade på reinforcement learning har framgångsrikt tillämpats på många olika maskininlärningsproblem. I denna rapport presenterar vi hur vi implementerar varianter på deep Q-learning-algoritmer på det klassiska datorspelet Snake. LÄS MER

  5. 5. DECISION-MAKING FOR AUTONOMOUS CONSTRUCTION VEHICLES

    Master-uppsats, Mälardalens högskola/Inbyggda system; Mälardalens högskola/Inbyggda system

    Författare :Gallardo Marielle; Chakraborty Sweta; [2019]
    Nyckelord :shared-space users; MPDM; timing analysis; planning and decision-making; autonomous vehicle; MDP; reinforcement learning; social force model;

    Sammanfattning : Autonomous driving requires tactical decision-making while navigating in a dynamic shared space environment. The complexity and uncertainty in this process arise due to unknown and tightly-coupled interaction among traffic users. LÄS MER