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 60 for “"Model Learning"”.
-
Efficient model learning for dialog management
… work develops several efficient algorithms for learning the POMDP parameters online and demonstrates them on dialog manager for a robotic wheelchair. In particular, we show how a combination of specialized queries ("meta-actions") can enable us to create a robust dialog manager that avoids the …
-
Residual Model Learning for Microrobot Control
… using compliant materials that are difficult to model analytically, limiting the utility of traditional model-based controllers. Challenges in data collection on microrobots and large errors between simulated models and real robots make current model-based learning and sim-to-real transfer …
-
Structured model learning for adaptive robot generalists
… sensory modalities, long-horizon reasoning, and learning from heterogeneous data sources. Traditional monolithic learning approaches remain brittle, lack modularity, and struggle to generalize across tasks, embodiments, and sensing configurations. This dissertation presents a unified framework …
-
Augmenting physics simulators with neural networks for model learning and control
… loss in precision. We propose a hybrid dynamics model, combining a deterministic physical simulator with a stochastic neural network for dynamics modeling as it provides us with expressiveness, efficiency, and generalizability simultaneously. To demonstrate this, we compare our hybrid model to …
-
Theoretical study of two prediction-centric problems : graphical model learning and recommendations
Motivated by prediction-centric learning problems, two problems are discussed in this thesis. PART I. Learning a tree-structured Ising model: We study the problem of learning a tree Ising model from samples such that subsequent predictions based on partial observations are accurate. Virtually all …
-
Reinforcement learning algorithms to model learning and decision-making in individuals with depressive disorders
… reviews attempts to use reinforcement learning models to improve the way we conceptualise some of the processes happening in the brain in mental illness. The hope is that more clearly defining the problems we are dealing with will eventually have a positive impact on our ability to …
-
Integrated motion planning and model learning for mobile robots with application to marine vehicles
… robots consider stochasticity in the dynamic model of the vehicle and the environment. A practical robust planning approach balances the duration of the motion plan with the probability of colliding with obstacles. This thesis develops fast analytic algorithms for predicting the collision …
-
An integrated performance model learning and planning approach for optimal infrastructure facility maintenance under partial observability
… observable problem. This thesis presents a learning and decision-making approach for developing optimal joint inspection and maintenance policies for civil infrastructure facilities under performance model uncertainty and partially observable condition state. Joint inspection and maintenance …
-
Learning environment simulators from sparse signals
… not been mapped out by hand, we need ways of learning environment models. While conventional work has focused on video prediction as a means for environment learning, this work instead seeks to learn from much sparser signals, like the agent's reward. In Chapter 1, we establish a taxonomy of …
-
Realistic Motion Estimation Using Accelerometers
… data-driven fashion, which includes two phases: model learning from an existing high quality motion database, and motion synthesis from the control signal. In the phase of model learning, we built a high quality motion model of less complexity that learned from a large motion capture database. …
-
Model-based approaches for learning control from multi-modal data
Methods like deep reinforcement learning (DRL) have gained increasing attention when solving very general continuous control tasks in a model-free end-to-end fashion. However, there has been great difficulty in applying these algorithms to real-world systems due to poor sample efficiency and …
-
Integration of Numerical Modeling and Field Observations of Deep Excavations
… SelfSim framework enhances our prediction and model learning capabilities from observed performance and represents a new opportunity to incorporate numerical simulations as an integral component in the application of the observational method in geotechnical engineering.
-
Robust learning of probabilistic hybrid models
… that system. For this reason, accurate models are essential for continued advancements in the field of autonomy. Hybrid stochastic models, such as JMLS and LPHA, allow for representational accuracy of a general scope of problems. The goal of this thesis is to develop a robust method for …
-
Modeling and control of a self-assembled robotic swimmer
This thesis presents a control strategy based on model learning for a self-assembled robotic “swimmer”. The swimmer forms when a liquid suspension of ferro-magnetic micro-particles and a non-magnetic bead are exposed to an alternating magnetic field that is oriented per- pendicular to the liquid …
-
Generative modeling of sequential data
… we investigate various approaches for generative modeling, with a special emphasis on sequential data. Namely, we develop methodologies to deal with issues regarding representation (modeling choices), learning paradigm (e.g. maximum likelihood, method of moments, adversarial training), and …
-
Latencies in paired-associate learning with normal and retarded children
… task within the frame-work of an all-or-none model learning in which the TLE was considered to be the pivot point of learning and in which only the associative "hook-up" phase of learning was studied. The variables studied were latencies and response scores. The results of the present study …
-
Generalizable Long-Horizon Robotic Manipulation under Uncertainty and Partial Observability
… a method for sequencing low-level reinforcement learning skills alongside information gathering actions, enabling increased task complexity and robustness in real-world tasks. Lastly, we show how large language models may be leveraged for few-shot model learning, allowing agents to rapidly adapt …
-
Subdominance Minimization: A Satisficing Perspective on Imitation Learning
… objectives. However, prevailing imitation learning methods tend to prioritize optimizing a single imitation objective. This myopic focus on a singular objective frequently leads to unintended and undesirable behaviors in learned models. For example, an autonomous vehicle prioritizing travel …
-
State discovery for autonomous learning
… to the study of algorithms for early perceptual learning for an autonomous agent in the presence of feedback. In the framework of associative perceptual learning with indirect supervision, three learning techniques are examined in detail: * short-term on-line memory-based model learning; * …
-
Robot learning with strong priors
Embedding learning ability in robotic systems is one of the long sought-after objectives of artificial intelligence research. Despite the recent advancements in hardware, large-scale machine learning algorithms and theoretical understanding of deep learning, it is still quite unrealistic to deploy …
Page 1 of 3