Sökning: "q-value"
Visar resultat 1 - 5 av 15 uppsatser innehållade ordet q-value.
1. Explainable AI for Multi-Agent Control Problem
Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : This report presents research on the application of policy explanation techniques in the context of coordinated reinforcement learning (CRL) for mobile network optimization. The goal was to improve the interpretability and comprehensibility of decision-making processes in multi-agent environments, with a particular focus on the Remote Antenna Tilt (RET) problem. LÄS MER
2. Standing Selfish and Grand? - A study of private equity impact on IPO valuation
D-uppsats, Handelshögskolan i Stockholm/Institutionen för finansiell ekonomiSammanfattning : The conflicting effects of private equity certification and grandstanding in relation to IPO underpricing has been disputed since the 1990's. Using a sample of 334 IPOs on six Swedish trading platforms, applying a Tobin's Q value relative as an alternative to first-day returns, this thesis finds differences in valuations between private equity and non-private equity backed IPOs. LÄS MER
3. Tunnel Seismic Prediction in Stockholm Bypass
Master-uppsats, KTH/Jord- och bergmekanikSammanfattning : Tunnel Seismic Prediction (TSP) is a geophysical investigation method used to predict the rock conditions ahead of the tunnel face. The method has been used in different types of rock and rock conditions. LÄS MER
4. How Stellar Tides Affect Planet Evolution
Kandidat-uppsats, Lunds universitet/Astronomi - Genomgår omorganisationSammanfattning : Planets that orbit their host star closely experience tidal forces due to the strength of gravity not being uniform all over the planet. This leads to effects such as tidal spin synchronization, tidal eccentricity damping and tidal semi-major axis damping. LÄS MER
5. Reinforcement Learning– Intelligent Weighting of Monte Carlo and Temporal Differences
Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknikSammanfattning : In Reinforcement learning the updating of the value functions determines the information spreading across the state/state-action space which condenses the valuebased control policy. It is important to have an information propagation across the value domain in a manner that is effective. LÄS MER