Sökning: "deep Q-network"

Visar resultat 1 - 5 av 7 uppsatser innehållade orden deep Q-network.

  1. 1. Investigation of Different Observation and Action Spaces for Reinforcement Learning on Reaching Tasks

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

    Författare :Ching-An Wu; [2019]
    Nyckelord :;

    Sammanfattning : Deep reinforcement learning has been shown to be a potential alternative to a traditional controller for robotic manipulation tasks. Most of modern deep reinforcement learning methods that are used on robotic control mostly fall in the so-called model-free paradigm. LÄS MER

  2. 2. Det som är Roligt, är Roligt

    Kandidat-uppsats,

    Författare :Anton Berg; [2019]
    Nyckelord :Artificial Intelligence; Reinforcement Learning; Deep Learning; Deep Q-Network; Enjoyability; Video Game; First Person Shooter; Unreal Tournament 2004; Optimality;

    Sammanfattning : This thesis explores the perceived enjoyability of Deep Reinforcement learning AI agents (DeepRL agent) that strives towards optimality within the First Person Shooter game Unreal Tournament 2004 (UT2004). The DeepRL agent used in the experiments was created and then trained within this game against the AI agent which comes with the UT2004 game (known here as a trivial UT2004 agent). LÄS MER

  3. 3. DQN Tackling the Game of Candy Crush Friends Saga : A Reinforcement Learning Approach

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

    Författare :Alice Karnsund; [2019]
    Nyckelord :;

    Sammanfattning : This degree project presents a reinforcement learning (RL) approach called deep Q-network (DQN) for learning how to play the game Candy Crush Friends Saga (CCFS). The DQN algorithm is implemented together with three extensions, which in 2015 resulted in a new state-of-the-art on the Atari 2600 domain. LÄS MER

  4. 4. AI in Simulated 3D Environments : Application to Cyber-Physical systems

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

    Författare :Clément Sevy; [2019]
    Nyckelord :;

    Sammanfattning : Over the past several years, UAVs (unmanned aerial vehicles) and autonomous systems in general, have become hot topics, both in academia and in industry. Indeed, the opportunities for the application of such technologies are vast, with the military and the infrastructure industry being the two most eminent cases. LÄS MER

  5. 5. Autonoma drönare : modifiering av belöningsfunktionen i airsim

    Kandidat-uppsats, Högskolan i Borås/Akademin för bibliotek, information, pedagogik och IT; Högskolan i Borås/Akademin för bibliotek, information, pedagogik och IT

    Författare :Elvir Dzeko; Markus Carlsson; [2018]
    Nyckelord :Autonomous; drones; dqn; reinforcement learning; neural network; AirSim; Autonom; drönare; AirSim; reinforcement learning; neuronnät;

    Sammanfattning : Inom det heta forskningsområdet med självflygande drönare sker det en kontinuerlig utveckling både inom forskningen och inom industrin. Det finns flera forskningsproblem kring autonoma fordon, inklusive autonom styrning av drönare. Ett intressant spår för autonom styrning av drönare, är via deep reinforcement learning, dvs. LÄS MER