Sökning: "Neuroevolution"
Visar resultat 1 - 5 av 12 uppsatser innehållade ordet Neuroevolution.
1. How does the performance of NEAT compare to Reinforcement Learning?
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This study examined the relative performance of Deep Reinforcement Learning compared to a neuroevolution algorithm called NEAT when used to train AIs in a discrete game environment. Today there are many AI techniques to choose from among which NEAT and RL have become popular alternatives. LÄS MER
2. Developmental Encodings in Neuroevolution - No Free Lunch but a Peak at the Menu is Allowed
Master-uppsats, Högskolan Dalarna/Institutionen för information och teknikSammanfattning : NeuroEvolution besides deep learning is considered the most promising method to train and optimize neural networks. Neuroevolution uses genetic algorithms to train the controller of an agent performing various tasks. LÄS MER
3. A scalable species-based genetic algorithm for reinforcement learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Existing methods in Reinforcement Learning (RL) that rely on gradient estimates suffer from the slow rate of convergence, poor sample efficiency, and computationally expensive training, especially when dealing with complex real-world problems with a sizable dimensionality of the state and action space. In this work, we attempt to leverage the benefits of evolutionary computation as a competitive, scalable, and gradient-free alternative to training deep neural networks for RL-specific problems. LÄS MER
4. Childhood Habituation in Evolution of Augmenting Topologies (CHEAT)
Master-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisationSammanfattning : Neuroevolution is a field within machine learning that applies genetic algorithms to train artificial neural networks. Neuroevolution of Augmenting Topologies (NEAT) is a method that evolves both the topology of the network and trains the weights of the network at the same time, and has been found to successfully solve reinforcement learning problems efficiently and the XOR problem with a minimal topology. LÄS MER
5. Adaptiv AI i spel och dess påverkan på det upplevda underhållningsvärdet
Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologiSammanfattning : .... LÄS MER