Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 5 of 5 for “"Q-Learning, SARSA"”.
-
Využití Robotického operačního systému (ROS) pro řízení kolaborativního robota UR3
… předem simulovaných trajektorií algoritmů Q-learning, SARSA, Deep Q-learning, Deep SARSA, a nebo za pomocí pouze frameworku MoveIT. V práci je pojednáno průřezem o tématech kolaborativní robotiky, Robotického operačního systému, simulačního prostředí Gazebo, zpětnovazebního a hluboké …
-
Optimising arrival management in air traffic control
… arrival management problem in a reinforcement learning framework. We design a basic air traffic model and apply both table representation methods and nonlinear approximation with a neural network. Specifically, we compare the performance of Q-learning, SARSA, and DDPG on this environment. …
-
Reinforcement learning based resource allocation in fog computing
… computing environments. First, a reinforcement learning-based method is introduced to optimize resource allocation for a single fog node. By formulating the problem as a Markov Decision Process (MDP), the approach maximizes fog resource utilization while considering the number of resource blocks …
-
Essays on Traditional and Emerging Transportation Issues
… a framework and application of reinforcement learning to a supply chain management problem. The last two papers are joint works with my co-advisor Suman Mallik and my research collaborator Nagarajan Sethuraman. The last two focus on studying autonomous vehicles insurance from an operations …
-
Reinforcement Learning-Based Test Case Generation with Test Suite Prioritization for Android Application Testing
… Android applications that combines reinforcement learning and test suite prioritization. These approaches aim to improve the effectiveness of the testing process by employing reinforcement learning algorithms, namely Q-learning and SARSA (State-Action-Reward-State-Action), for automated test case …