Sökning: "markov decision process"

Visar resultat 1 - 5 av 18 uppsatser innehållade orden markov decision process.

  1. 1. A Partially Observable Markov Decision Process for Breast Cancer Screening

    Master-uppsats, Linköpings universitet/Statistik och maskininlärning

    Författare :Joshua Hudson; [2019]
    Nyckelord :POMDP; Markov Decision Process; Breast Cancer; Screening; Operations Research;

    Sammanfattning : In the US, breast cancer is one of the most common forms of cancer and the most lethal. There are many decisions that must be made by the doctor and/or the patient when dealing with a potential breast cancer. LÄS MER

  2. 2. Transfer of reinforcement learning for a robotic skill

    Master-uppsats, Luleå tekniska universitet/Datavetenskap

    Författare :Dulce Adriana Gómez Rosal; [2018]
    Nyckelord :Transfer learning; Reinforcement learning; Simulation; Robotics;

    Sammanfattning : In this work, we develop the transfer learning (TL) of reinforcement learning (RL) for the robotic skill of throwing a ball into a basket, from a computer simulated environment to a real-world implementation. Whereas learning of the same skill has been previously explored by using a Programming by Demonstration approach directly on the real-world robot, for our work, the model-based RL algorithm PILCO was employed as an alternative as it provides the robot with no previous knowledge or hints, i. LÄS MER

  3. 3. Deep Reinforcement Learning in Real-time Bidding

    Kandidat-uppsats, Lunds universitet/Matematik LTH

    Författare :Oskar Stigland; [2018]
    Nyckelord :Machine learning; reinforcement learning; markov decision process; neural network; deep Q-network; real-time bidding; online display advertisement; Mathematics and Statistics;

    Sammanfattning : Real-time bidding is getting increasingly popular for buying and selling online display advertisement. This has spurred a research interest into how to design optimal bidding algorithms, with advances during the last two to three years focusing heavily on reinforcement learning. LÄS MER

  4. 4. Learning Operational Goals for Propulsion System Using Reinforcement Learning

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

    Författare :Johan Lewenhaupt; [2018]
    Nyckelord :;

    Sammanfattning : This degree project, conducted at ABB, aims to analyze and solve differentsituations that a crew on board a vessel might face by controllingits propulsion system. The propulsion system is viewed as static,transition-deterministic, as well as stochastic when measuring data. LÄS MER

  5. 5. Probabilistic Least-violating Control Strategy Synthesis with Safety Rules

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

    Författare :Ludvig Janiuk; Johan Sjölén; [2018]
    Nyckelord :;

    Sammanfattning : We consider the problem of automatic control strategy synthesis for discrete models of robotic systems, where the goal is to travel from some region to another while obeying a given set of safety rules in an environment with uncertain properties. This is a probabilistic extension of the work by Jana Tumová et al. LÄS MER