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 20 of 20 for “"Model-based Reinforcement Learning"”.
-
Tame Long-Horizon Model-Based Reinforcement Learning
Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across tasks. Model-based RL, on the other hand, learns task-agnostic …
-
Robust model-based reinforcement learning using L1 adaptive control
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01
-
An Application of Sliding Mode Control to Model-Based Reinforcement Learning
<p>The state-of-art model-free reinforcement learning algorithms can generate admissible controls for complicated systems with no prior knowledge of the system dynamics, so long as sufficient (oftentimes millions) of samples are available from the environ- ment. On the other hand, model-based …
-
Predictive Models for Visuomotor Feedback Control in Object Pile Manipulation
… In addition, how can we build predictive models over such representations that can be useful for their task-free generality? In the first chapter of this thesis, we investigate using the image observation directly as state, and compare different models that can be useful over this space of …
-
Solving planning problems with deep reinforcement learning and tree search
Deep reinforcement learning methods are capable of learning complex heuristics starting with no prior knowledge, but struggle in environments where the learning signal is sparse. In contrast, planning methods can discover the optimal path to a goal in the absence of external rewards, but often …
-
Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents
Performance of state-of-the art offline and model-based reinforcement learning (RL) algorithms deteriorates significantly when subjected to severe data scarcity and the presence of heterogeneous agents. In this work, we propose a model-based offline RL method to approach this setting. Using all …
-
Reinforcement learning in network control
… often unknown, and need to be learned. Existing reinforcement learning methods such as Q-Learning, Actor-Critic, etc. are heuristic and do not offer performance guarantees. In contrast, model-based learning methods offer performance guarantees, but can only be applied with bounded state spaces. …
-
Inferring Structured World Models from Videos
Advances in reinforcement learning have allowed agents to learn a variety of board games and video games at superhuman levels. Unlike humans - which can generalize to a wide range of tasks with very little experience - these algorithms typically need vast number of experience replays to perform at …
-
Understanding Vision-based Dynamics Models
Recent developments in vision-based dynamics models have helped researchers achieve state-of-the-art results in a number of fields. For instance, in model-based reinforcement learning, vision-based methods perform extremely well on a variety of games and control tasks while using orders of …
-
AUTOMATIC ROUTING OF SUBMARINE ELECTRICAL CABLES USING MACHINE LEARNING
… large minimum bend radius. These cables must be modeled using 3D CAD to ensure they are not bent past the minimum bend radius and to reduce the space consumed. This process is labor-intensive and sub-optimal. The objective of this thesis is to determine the feasibility of using the model-based …
-
Model-Based Learning and Planning for Intelligent Manipulation Using Probabilistic Hybrid Models
While the rapid advancement of deep learning and grasp-affordance grasping has allowed the fast planning of grasping poses directly from visual inputs, it still commonly adopts an open-loop architecture that has made it slow to react and prone to failure, limiting its use in more complicated …
-
Sample-Efficient Reinforcement Learning for Spoken Dialogue Systems
… to provide an optimal demonstrative response based on user inputs. Additionally, achieving the desired outcome often requires multiple turns of responses, and the consequences of an action may not manifest immediately. Consequently, dialogue management, which involves determining how to …
-
Stochastic prediction in sequential high-dimensional observation space
… of natural images require the predictive model to build an intricate understanding of the natural world. Many existing predictive methods tackle this problem by making simplifying assumptions about the environment. One common assumption is that the outcome is deterministic and there is …
-
Multiagent planning with Bayesian nonparametric asymptotics
… autonomous systems must incorporate some form of learning. However, learning techniques themselves often require structural assumptions to be made about the environment in which a system acts. Bayesian nonparametrics, on the other hand, possess structural flexibility beyond the capabilities of …
-
Learning Structured World Models From and For Physical Interactions
… multiple sensory modalities and build a mental model that predicts how the world would change if we applied a specific action (i.e., intuitive physics). This dissertation presents my research that draws on insights from humans and develops model-based reinforcement learning (RL) agents. The …
-
Integration of Control and Dynamical Systems Perspectives to Machine Learning
… in interdisciplinary research spanning machine learning -- a data-driven approach based on statistics -- and control or dynamical systems theory, which deals with dynamic environments. Because those streams of studies have evolved in a relatively separate manner under different settings and …
-
Improving Exploration in Reinforcement Learning through Domain Knowledge and Parameter Analysis
… novel work on how to improve exploration in reinforcement learning using domain knowledge and knowledge-based approaches to reinforcement learning. It also identifies novel relationships between the algorithms' and domains' parameters and the exploration efficiency. The goal of solving …
-
Robotic Olfactory-Based Navigation with Mobile Robots
… odor source is designing an effective olfactory-based navigation algorithm, which guides the robot to detect emitted odor plumes as cues in finding the source. This dissertation proposes three kinds of olfactory-based navigation methods to improve search efficiency while maintaining a low …
-
Safe online learning for nonlinear dynamical systems using control contraction metrics
This thesis aims to develop an online learning framework for a military fixed-wing aircraft that can adapt a control policy to unforeseen changes in the airframe’s flight dynamics. This is an active area of research and a significant challenge for high dimensional non linear systems due to the …
-
AI-based Detection Against Cyberattacks in Cyber-Physical Distribution Systems
… detection is also realized through detailed modeling of 5G and latency requirements are validated.