Sökning: "förstärkt inlärning"
Visar resultat 1 - 5 av 22 uppsatser innehållade orden förstärkt inlärning.
1. Comparing Four Modelling Methods for the Simulation of a Soft Quadruped Robot
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : A soft quadruped robot is being developed at the Department of Machine Design and Department of Production Engineering at KTH. The legs of the robot consist of four continuum actuators that can achieve complex movements. In order to efficiently develop gaits for the robot, reinforcement learning will be used. LÄS MER
2. The effects of multistep learning in the hard-exploration problem
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Reinforcement learning is a machine learning field which has received revitalised interest in later years due to many success stories and advancements in deep reinforcement learning. A key part in reinforcement learning is the need for exploration of the environment so the agent can properly learn the best policy. LÄS MER
3. Stratego Using Deep Reinforcement Learning and Search
Master-uppsats, KTH/Matematisk statistikSammanfattning : Algorithmic game theory is a research area concerned with developing algorithms for solving games using game-theoretic concepts, with many applications in areas where games are used as models to achieve knowledge. In the last decades, numerous game-playing bots have been created, and in many games, they outperform top humans. LÄS MER
4. Anomalidetektering i loggar med förstärkt inlärning
Kandidat-uppsats, Karlstads universitet/Fakulteten för hälsa, natur- och teknikvetenskap (from 2013)Sammanfattning : By using machine learning to monitor and find deviations in log data makes it easier for developers and can prevent a workflow from stopping. The goal of this project is to investigate if it is possible to find anomalies in log data using reinforcement learning. LÄS MER
5. Scaling up Maximum Entropy Deep Inverse Reinforcement Learning with Transfer Learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In this thesis an issue with common inverse reinforcement learning algorithms is identified, which causes them to be computationally heavy. A solution is proposed which attempts to address this issue and which can be built upon in the future. LÄS MER
