Sökning: "reward-based"
Visar resultat 1 - 5 av 37 uppsatser innehållade ordet reward-based.
1. Hundar i människans tjänst : kan det rättfärdigas?
Kandidat-uppsats, SLU/Dept. of Animal Environment and HealthSammanfattning : Människan insåg tidigt att vargen, och så småningom hunden, var en bra partner tack vare sitt utomordentliga luktsinne och sin förmåga att samarbeta. Det utnyttjades i jakt och krig och numera inom det moderna försvaret och rättsväsendet. LÄS MER
2. Equity-based Crowdfunding in the UK: Obtaining Subsequent Financing from a VC after a Successful Campaign
Magister-uppsats, Lunds universitet/Företagsekonomiska institutionenSammanfattning : Equity crowdfunding has achieved a high popularity in the UK throughout the last years. However, most researchers within this field primarily focused on the success factors of an equity crowdfunding campaign while only little is known about the post-campaign effects. LÄS MER
3. AI-Driven Meal Planning in the FoodTech Industry: A Reinforcement Learning Approach
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Traditional meal planning for large kitchens is a laborious and complex affair with multiple external constraints imposed on the meal plan, such as a healthy nutrition profile and a low environmental impact, which should be fulfilled while being under budget. This is a tough task for humans but by modelling the process with a Markov Decision Process and using Reinforcement Learning an agent can be taught to create meal plans from constraints. LÄS MER
4. Parameter Tuning in a Jet Printing Machine usingReinforcement Learning
Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)Sammanfattning : Surface mount technology is a common way to assembly electrical components onto PrintedCircuit Boards (PCB). To assemble the components, solder paste is used. One way to apply solderpaste onto PCB is jet printing. LÄS MER
5. Learning Sampling Strategies for Stochastic Gradient Descent using Deep Reinforcement Learning techniques
Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknikSammanfattning : 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