Sökning: "Backgammon"

Visar resultat 1 - 5 av 7 uppsatser innehållade ordet Backgammon.

  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

  3. 2. Development of an Artificial Intelligent Software Agent using Artificial Intelligence and Machine Learning Techniques to play Backgammon Variants

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

    Författare :Aristotelis Kostias; Georgios Tagkoulis; [2018]
    Nyckelord :Artificial Intelligence; Neural Network; Software Agents; Reinforcement Learning; Backgammon; Swedish Tables; Artificiell intelligens; Neuralt nätverk; Mjukvara agenter; Förstärkande lärande; Backgammon; Svenska tabeller;

    Sammanfattning : Artificial Intelligence has seen enormous progress in many disciplines in the recent years. Particularly, digitalized versions of board games require artificial intelligence application due to their complex decision-making environment. Game developers aim to create board game software agents which are intelligent, adaptive and responsive. LÄS MER

  4. 3. Development and simulation of an active target detector with GEM foil readout

    Master-uppsats, Lunds universitet/Fysiska institutionen; Lunds universitet/Kärnfysik

    Författare :Elisabeth Rickert; [2017]
    Nyckelord :Physics and Astronomy;

    Sammanfattning : At CERN, radioactive ion beams with energies of up to 10 MeV/u can be pro- duced by a newly commissioned post-accelerator, HIE-ISOLDE, which expands the possibilities for nuclear reaction studies. To investigate the collision properties of the ion beam with a target, an active gas–target detector is under development by the Reactions Group at the Nuclear Physics Division in Lund. LÄS MER

  5. 4. Deep reinforcement learning compared with Q-table learning applied to backgammon

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Peter Finnman; Max Winberg; [2016]
    Nyckelord :;

    Sammanfattning : Reinforcement learning attempts to mimic how humans react to their surrounding environment by giving feedback to software agents based on the actions they take. To test the capabilities of these agents, researches have long regarded board games as a powerful tool. LÄS MER

  7. 5. Aesthetic Details and Player Behavior : a study on how the colors of checkers in backgammon affect players’ choices of action

    Kandidat-uppsats, Institutionen för speldesign, teknik och lärande

    Författare :Andreas Bergqvist; [2013]
    Nyckelord :Backgammon; Color; Behavior; Choice of Action; Player; the Proteus Effect; Board Games; Self-perception; Self-representation;

    Sammanfattning : Based upon earlier studies in the fields of psychology and game design by Frank and Gilovich (1988) and Yee (2007), this paper examines the influence of color on players of backgammon. The paper examines the probability of a player hitting an opponent’s piece when possible in backgammon depending on the color of the checkers. LÄS MER