The full text of this item is not available at this time because the student has placed this item under an embargo for a period of time. The Libraries are not authorized to provide a copy of this work during the embargo period, even for Texas A&M users with NetID.
Enhancing Reinforcement Learning Using Data and Structure
Abstract
Reinforcement learning is a powerful approach for training intelligent agents to make decisions in complex environments. However, these algorithms often struggle when faced with challenging scenarios, such as sparse reward feedback or environments with multiple learning agents. Additionally, the requirement for a large number of training samples makes real-world deployment difficult. In this work, we present novel reinforcement learning algorithms that leverage data and structure to enhance the learning process and overcome these challenges. Specifically, we introduce new RL algorithms that leverage demonstration data to guide learning in sparse reward environments, exploit structural similarity and data to accelerate learning in such environments, use structure to learn in environments with multiple agents, and learn from data distributed among multiple clients without sharing the data. The proposed algorithms show promising results and offer potential for practical applications in complex and diverse environments.
Subject
Reinforcement LearningLearning from Demonstrations
Meta Reinforcement Learning
Federated Learning
Mean Field Reinforcement Learning
Citation
Rengarajan, Desik (2023). Enhancing Reinforcement Learning Using Data and Structure. Doctoral dissertation, Texas A&M University. Available electronically from https : / /hdl .handle .net /1969 .1 /199816.
Related items
Showing items related by title, author, creator and subject.
-
Peterson, Cheryl (2012-10-19)PlantingScience (PS) is a unique web-based learning system designed to develop secondary students' scientific practices and proficiencies as they engage in hands-on classroom investigations while being mentored online by ...
-
Guimaraes Goecks, Vinicius (2020-03-17)Recent successes combine reinforcement learning algorithms and deep neural networks, despite reinforcement learning not being widely applied to robotics and real world scenarios. This can be attributed to the fact that ...
-
Hasanzadehmoghimi, Arman (2021-12-03)In this dissertation, we propose novel Bayesian machine learning models to solve various graph analytics problems, including graph representation learning, graph generative modeling, structured semi-supervised learning, ...