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 24 for “"Model-free learning"”.
-
Model-free learning with imitation
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Applications of model-free learning in wireless networks
… control problems are frequently addressed in the model-based paradigm. However, due to the practical limitation of information incompleteness/locality, directly applying the model-based solutions will face difficulties. As a result, the method of controlling-by-learning without the need for the a …
-
Secure, Intermittent, and Model-Free Learning Framework for Autonomous Cyber Physical Systems
… In an adversarial, information-constrained, and model-agnostic environment, reinforcement learning (RL) methods design optimal control policies using reward signals that possess decentralized learning and deployment protocols. Increased continuous data-sharing between sensors, actuators, and the …
-
Analytical and experimental comparison of model-based, model -free, and hybrid learning control of active and passive building thermal storage inventory
… and passive building thermal storage inventory. Model-based predictive optimal control, model-free learning control, and a hybrid learning but model-based control scheme were investigated successively. Numerical analysis and experimental study demonstrated that each of these approaches has …
-
Model Free Optimal Control Approach for UAVs
This thesis discusses use of model free control algorithms for application on an UAV. The work contrasts use of LQR based methods to conventional model free learning based on neural net approximators which do not provide guarantees of optimal solution. The model free control methods discussed here …
-
Learning and acting in unknown and uncertain worlds
This dissertation addresses the problem of learning to act in an unknown and uncertain world. This is a difficult problem. Even if a world model is available, an assumption not made here, it is known to be intractable to learn an optimal policy for controlling behaviour (Littman 1996). Assuming no …
-
Breaking Apart the Reinforcement Learning Deficit in Schizophrenia
Reinforcement learning deficits have long been associated with schizophrenia. However, tasks traditionally used to assess these deficits often rely on multiple processing streams leaving the etiology of these task deficits unclear. In the current study, we borrowed a recent framework from …
-
Stochastic Model Predictive Control via Fixed Structure Policies
In this work, the model predictive control problem is extended to include not only open-loop control sequences but also state-feedback control laws by directly optimizing parameters of a control policy. Additionally, continuous cost functions are developed to allow training of the control policy in …
-
Interpretable approaches for condition monitoring, control, and energy optimization in electro-hydrostatic actuation systems
… Bayesian optimization is used for tuning of its model parameters. On the control front, the limitations and challenges of the model-based controller are investigated. To circumvent these challenges, a model-free learning strategy is introduced, consisting of offline and online phases. The …
-
Heuristics and Recency Effect for Large Rare Rewards: Humans vs. Large Language Models
… but overweight extreme rewards. Moreover, value-free heuristics have also been shown to be useful in guiding choices without requiring value/utility estimation, especially in high-uncertainty environments. This raises an open question as to whether individuals rely on value estimation or …
-
Hybrid Modeling and Simulation of Stochastic Effects on Biochemical Regulatory Networks
… in the presence of inevitable noise. Stochastic modeling is viewed as a key paradigm to study the effects of intrinsic and extrinsic noise on the dynamics of biochemical networks. A detailed quantitative description of such complex and multiscale networks via stochastic modeling poses several …
-
Συμβολή στην ανάπτυξη πολυπρακτορικής αρχιτεκτονικής αναπτυξιακού ρομποτικού ελέγχου στη βάση ασαφούς ενισχυτικής μάθησης: εφαρμογή στον επιδέξιο ρομποτικό χειρισμό
This thesis proposes a model-free learning mechanism based on a nested hierarchical multi-agent architecture, which is applied in the context of dexterous robot manipulation control. In the proposed multi-agent system, each agent forms a local (partial) view of the global system state and task …
-
The Depressed Decision Maker: The Application of Decision Science to Psychopathology
… across a range of decision tasks, but impaired learning and pessimism bias showed the strongest behavioral signature of depression. Decision tasks significantly predict depression, but are far outperformed by self-report measures as diagnostic tools. Overall, results suggest decision tasks are …
-
Data-Driven Control with Learned Dynamics
… dynamics that are actively learned from machine learning algorithms. With system dynamics being identified using neural networks either explicitly or implicitly, we can apply control following either a model-based approach or a model-free approach. In this thesis, the two different methods are …
-
Design Distributed Control and Learning Algorithms for a Team of UAVs for Optimal Field Coverage
… the problem by two distinct approaches: one is model-based and the other is model-free. In the first part, we proposed a model-based control framework for UAV teaming to monitor and track a dynamic field like wildfire spreading. Wildfire is well-known for their destructive ability to inflict …
-
Learning in Large Interactive Environments
In both Planning and Reinforcement Learning, an interactive environment is a dynamic system with which an agent interacts to achieve its goals. In planning, the agent uses its knowledge of the environment to generate a plan offline and then executes it in the interactive environment, adapting if …
-
Learning for Cross-layer Resource Allocation in the Framework of Cognitive Wireless Networks
… without knowing in advance an accurate network model. We study a series of cross-layer resource allocation problems in cognitive wireless networks. Based on model-free learning, optimization and game theory, we propose a framework of self-organized, adaptive strategy learning for wireless …
-
Efficient Methods for Distributed Machine Learning and Resource Management in the Internet-of-Things
… at the intersection of optimization, machine learning, and networked systems. Specifically, the research objectives and innovative claims include: (T1) Scalable distributed machine learning approaches for efficient IoT implementation; and, (T2) Enhanced resource management policies for IoT by …
-
Reinforcement Learning for Stochastic Control and Games in Algorithmic Trading
… the problem by developing a modified Deep Q-Learning method for a single agent trader, generalizing the approach for multi-agent games using Nash equilibria, and constructing a new method for generating arbitrage-free implied volatility surfaces used for derivative pricing. The thesis …
-
Efficient Environment Sensing and Learning for Mobile Robots
Data-driven learning is becoming an integral part of many robotic systems. Robots can be used as mobile sensors to learn about the environment in which they operate. Robots can also seek to learn essential skills, such as navigation, within the environment. A critical challenge in both types of …
Page 1 of 2