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 “"Model-based deep reinforcement learning"”.
-
Cooperative Payload Transportation by UAVs: A Model-Based Deep Reinforcement Learning (MBDRL) Application
We propose a Model-Based Deep Reinforcement Learning (MBDRL) framework for collaborative paylaod transportation using Unmanned Aerial Vehicles (UAVs) in Search and Rescue (SAR) missions, enabling heavier payload conveyance while maintaining vehicle agility. Our approach extends the single-drone …
-
Model-Based Deep Reinforcement Learning for Optimal Fuel-Efficient Routing and Traffic Signal Control
This dissertation presents a model-based deep reinforcement learning (MB-DRL)framework, inspired by the AlphaGo Zero architecture, and demonstrates its application to twosequential optimization problems in intelligent transportation systems. The primary contributionis methodological: the MB-DRL …
-
Exploration-Exploitation Trade-Off in Reinforcement Learning
… trade-off is a fundamental challenge in reinforcement learning. Recent applications of reinforcement learning in large language models and world models have further underscored the critical need for principled, scalable, and efficient exploration algorithms. Exploration has been …
-
Exploration-Exploitation Trade-Off in Reinforcement Learning
… trade-off is a fundamental challenge in reinforcement learning. Recent applications of reinforcement learning in large language models and world models have further underscored the critical need for principled, scalable, and efficient exploration algorithms. Exploration has been …
-
Deep Learning for Spatially and Temporally Resolved Materials Systems
Leveraging deep learning (DL) in materials research can significantly accelerate the materials design and discovery process. In this document, I demonstrate how a data hungry technique like DL can be used to replace complex techniques in temporally resolved materials systems and for identifying key …