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 10 of 10 for “"Constrained reinforcement Learning"”.
-
Constrained Reinforcement Learning for Wireless Networks
… This structure enables us to design an efficient constrained reinforcement learning (CRL) algorithm to learn it. Specifically, we show using the structure of the problem that a three time scale stochastic approximation based policy gradient algorithm can learn the globally optimal policy. We …
-
ONLINE DECISION MAKING FOR DYNAMICAL SYSTEMS: MODEL-BASED AND DATA-DRIVEN APPROACHES
… tools from control theory, optimization, and learning to address the problem of online decision-making for dynamical systems, considering streaming data and dynamically changing information. Two online decision-making frameworks are presented in this thesis, depending on the availability of …
-
Safe reinforcement learning in automotive
This work applies Logically Constrained Reinforcement Learning (LCRL) frame-work for synthesizing policies for active monitoring and management of sensor modules in autonomous vehicles. LCRL allows synthesizing policies for unknown and continuous-state Markov Decision Processes (MDPs) such that a …
-
Safe Multi-Robot Planning Via Long-Run Averages
Constrained reinforcement learning in Markov decision processes (MDPs) has received increasing attention for its use in sequential decision making problems with safety requirements. This study investigated safe planning via long run average reward using MDPs. This thesis uses grid-world …
-
Reinforcement Learning-Assisted Spacecraft Trajectory Design and Guidance Using Structured Control Laws
Spacecraft trajectory planning is fundamentally a constrained dynamical decision problem in which mission objectives must typically be achieved under nonlinear dynamics, limited control authority, uncertainty, and strict state and control constraints. Classical trajectory optimization and feedback …
-
Graph-based Learning for Efficient Resource Allocation in Wireless Networks under Constraints
… yet sub-optimal at best. Recently, deep learning algorithms have been extensively employed to obtain approximate solvers efficiently. In particular, graph-based models have been shown to be most effective in leveraging the irregular connectivity structure of wireless networks. In this …
-
Control and Optimization over Large-Scale Networks
… in the first part of this work we present a constrained reinforcement learning framework for the joint design of control and communication policies that optimizes the performance of the control system while satisfying requirements on the usage of communication resources. As the scale of …
-
A Trustworthy Deep Reinforcement Learning Framework for Slicing in Next-Generation Open Radio Access Networks
… meet their performance requirements. While deep reinforcement learning (DRL) has shown promise in managing inter-slice resource allocation (RA), its practical application faces several challenges, such as generalization and safety, which hinder the widespread adoption of DRL algorithms in real …
-
Advanced reinforcement learning methods for autonomous navigation of unmanned surface vessels
… from surrounding obstacles. While deep reinforcement learning (DRL) provides a promising framework for learning navigation policies through interaction with an environment, its application to autonomous maritime navigation remains constrained by issues related to safety, the availability …