Sökning: "Reward Function"

Visar resultat 1 - 5 av 51 uppsatser innehållade orden Reward Function.

  1. 1. Not All Goals Are Created Equal : Evaluating Hockey Players in the NHL Using Q-Learning with a Contextual Reward Function

    Master-uppsats, Linköpings universitet/Databas och informationsteknik

    Författare :Jon Vik; [2021]
    Nyckelord :Sports Analytics; Markov Game; Machine Learning; Reinforcement Learning; Q-Learning; Data Mining; National Hockey League; Ice Hockey; Reward Function; Player Evaluation;

    Sammanfattning : Not all goals in the game of ice hockey are created equal: some goals increase the chances of winning more than others. This thesis investigates the result of constructing and using a reward function that takes this fact into consideration, instead of the common binary reward function. LÄS MER

  2. 2. Domain Transfer for End-to-end Reinforcement Learning

    Uppsats för yrkesexamina på avancerad nivå, Högskolan i Halmstad/Akademin för informationsteknologi; Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Anton Olsson; Felix Rosberg; [2020]
    Nyckelord :Reinforcement Learning; Domain Transfer; Deep Deterministic Policy Gradient; Reinforcement Learning in Real-time;

    Sammanfattning : In this master thesis project a LiDAR-based, depth image-based and semantic segmentation image-based reinforcement learning agent is investigated and compared forlearning in simulation and performing in real-time. The project utilize the Deep Deterministic Policy Gradient architecture for learning continuous actions and was designed to control a RC car. LÄS MER

  3. 3. Den ideella ledaren : En studie som undersöker personlighetstyper kopplat till utbrändhet tillsammans med motivationsfaktorer inom svenska idrottsföreningar

    Kandidat-uppsats, Högskolan i Gävle/Företagsekonomi; Högskolan i Gävle/Företagsekonomi

    Författare :Rebecca Gullersbo; Felicia Steiner; [2020]
    Nyckelord :“The Big Five”; “Maslach Burnout Inventory”; “Maslach Burnout Inventory- General survey”; utbrändhet; personality traits; volontär; “Volunteer Function Inventory”; coach; sport.;

    Sammanfattning : Abstract   Title: The nonprofit leader   Level: Final assignment for Bachelor Degrees in Business Administration   Author: Felicia Jingmyr Steiner and Rebecca Gullersbo   Supervisor: Jonas Kågström   Date: May 2020   Aim: The purpose is to highlight the connection between Big Five´s different personality traits, the dimension according the Maslach Burnout Inventory and the underlying motivational factors within Swedish sport associations and their non-profit leaders.   Method: The study uses a quantitive method with a deductive approach. LÄS MER

  4. 4. Learning Sampling Strategies for Stochastic Gradient Descent using Deep Reinforcement Learning techniques

    Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknik

    Författare :Hampus Rosvall; [2020]
    Nyckelord :Technology and Engineering;

    Sammanfattning : Solving finite-sum minimization problems could be done by the use of a gradient descent algorithm. The algorithm evaluates the gradient with respect to the current state of the parameters and updates the parameters in the direction of the steepest descent. LÄS MER

  5. 5. Comparison of autonomous waypoint navigation methods for an indoor blimp robot

    Master-uppsats, KTH/Mekatronik; KTH/Mekatronik

    Författare :Lukas Prusakiewicz; Simon Tönnes; [2020]
    Nyckelord :UAV; indoor airship; blimp; path planning; reinforcement learning; RRT; autonomous navigation; UAV; inomhus luftskepp; blimp; path planning; förstärkningsinlärning; RRT; autonom navigering;

    Sammanfattning : The Unmanned Aerial Vehicle (UAV) has over the last years become an increasingly prevalent technology in several sectors of modern society. Many UAVs are today used in a wide series of applications, from disaster relief to surveillance. A recent initiative by the Swedish Sea Rescue Society (SSRS) aims to implement UAVs in their emergency response. LÄS MER