Sökning: "Reward Function"
Visar resultat 21 - 25 av 85 uppsatser innehållade orden Reward Function.
21. Improving a Reinforcement Learning Algorithm for Resource Scheduling
Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknikSammanfattning : This thesis aims to further investigate the viability of using reinforcement learning, specifically Q-learning, to schedule shared resources on the Ericsson Many-Core Architecture (EMCA). This was first explored by Patrik Trulsson in his master thesis Dynamic Scheduling of Shared Resources using Reinforcement Learning (2021). LÄS MER
22. Decision-support tool for identifying locations of shared mobility hubs : A case study in Amsterdam
Master-uppsats, KTH/TransportplaneringSammanfattning : Shared mobility is considered a more sustainable alternative to private modes. Nonetheless, its sudden and sometimes “out of control” emergence poses issues that need to be addressed. LÄS MER
23. Benchmarking Deep Reinforcement Learning on Continuous Control Tasks : AComparison of Neural Network Architectures and Environment Designs
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep Reinforcement Learning (RL) has received much attention in recent years. This thesis investigates how reward functions, environment termination conditions, Neural Network (NN) architectures, and the type of the deep RL algorithm aect the performance for continuous control tasks. LÄS MER
24. Risk Averse Path Planning Using Lipschitz Approximated Wasserstein Distributionally Robust Deep Q-Learning
Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknikSammanfattning : We investigate the problem of risk averse robot path planning using the deep reinforcement learning and distributionally robust optimization perspectives. Our problem formulation involves modelling the robot as a stochastic linear dynamical system, assuming that a collection of process noise samples is available. LÄS MER
25. Explainable Reinforcement Learning for Risk Mitigation in Human-Robot Collaboration Scenarios
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Reinforcement Learning (RL) algorithms are highly popular in the robotics field to solve complex problems, learn from dynamic environments and generate optimal outcomes. However, one of the main limitations of RL is the lack of model transparency. This includes the inability to provide explanations of why the output was generated. LÄS MER