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 75 for “"Model-based Reinforcement Learning"”.
-
Dimensionless Bayesian Model-Based Reinforcement Learning
… an approach for improving the robustness of Model-Based Reinforcement Learning algorithms by transforming the observation and decision spaces with the Buckingham-Π theorem. This theorem is part of the field of Dimensional Analysis (DA) which studies the link between physical measurements and …
-
MODEL-BASED REINFORCEMENT LEARNING FOR COMPLEX ENVIRONMENTS
Deep reinforcement learning (DRL) has achieved great success in sophisticated games, such as Atari, Go, etc. Compared with classic planning methods that explicitly reason handcrafted and potentially inaccurate dynamic models, standard DRL methods directly map raw observations to a policy, which …
-
Optimal planning with approximate model-based reinforcement learning
Model-based reinforcement learning methods make efficient use of samples by building a model of the environment and planning with it. Compared to model-free methods, they usually take fewer samples to converge to the optimal policy. Despite that efficiency, model-based methods may not learn the …
-
Model-based Reinforcement Learning of Nonlinear Dynamical Systems
Model-based Reinforcement Learning (MBRL) techniques accelerate the learning task by employing a transition model to make predictions. In this dissertation, we present novel techniques for online learning of unknown dynamics by iteratively computing a feedback controller based on the most recent …
-
Model-based reinforcement learning with small sample size
State-of-the-art reinforcement learning (RL) algorithms generally require a large sample of interaction data to learn sufficiently well, which makes it difficult to apply them to the problems where data is expensive. This thesis studies exploration, transformation bias, and policy selection of …
-
Model-based Reinforcement Learning Methods for Developing Intelligent Assistants
… without explicit instruction. I show that model-based reinforcement learning is a particularly appropriate class of methods to pursue. Next, I provide a sample-efficient model-based reinforcement learning method: soft-planner policy optimization. In this method, we introduce a novel …
-
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
-
World Model Uncertainty for Sample Efficient Model-Based Reinforcement Learning
To facilitate the deployment of Reinforcement Learning (RL) agents on real-world robots, Model-Based Reinforcement Learning (MBRL) addresses data inefficiency by using a world model to simulate the real environment, thereby minimising wear and tear on mechanical components. Uncertainty has emerged …
-
Deep Model-Based Reinforcement Learning for Sample Efficient Predictive Control
Deep reinforcement learning algorithms provide a framework for learning high performance solutions to complex problems without explicit knowledge of the systems with which the algorithms are interacting. These algorithms are of particular interest for the fields of control and robotics, which …
-
The effects of dopaminergic modulation on model-based reinforcement learning
… in humans, both of which are important in learning and decision making. Moreover, dysfunction in the brain's dopamine circuits and mechanisms of decision making is observed during acute stress.</p> <p>Mammals are thought to use two evaluation strategies in decision making, model-based and …
-
Risk-sensitive and robust model-based reinforcement learning and planning
… this thesis, we will address both planning and reinforcement learning (RL) approaches to sequential decision-making. In the planning setting, it is assumed that a model of the environment is provided, and a policy is optimised within that model. Reinforcement learning relies upon extensive …
-
Model-based reinforcement learning for integrated radar and communications systems
… optimization approaches that are incapable of learning from experiences and are susceptible to modeling deficiencies. Therefore, this thesis adopts a data-driven reinforcement learning (RL) approach for optimizing resource allocations and waveforms in ISAC systems. In particular, the focus is …
-
An Application of Sliding Mode Control to Model-Based Reinforcement Learning
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 …
-
Leveraging Value-awareness for Online and Offline Model-based Reinforcement Learning
Model-based Reinforcement Learning (RL) lies at the intersection of planning and learning for sequential decision making. Value-awareness in model learning has recently emerged as a means to imbue task or reward information into the objective of model learn- ing, in order for the model to leverage …
-
A spiking neural network of state transition probabilities in model-based reinforcement learning
The development of the field of reinforcement learning was based on psychological studies of the instrumental conditioning of humans and other animals. Recently, reinforcement learning algorithms have been applied to neuroscience to help characterize neural activity and animal behaviour in …
-
Model-based reinforcement learning and deep learning for power converter circuit design automation
… framework for power converter design, leveraging reinforcement learning (RL) and graph-transformer networks (GTN) to address critical inefficiencies in traditional manual topology optimization. Motivated by the combinatorial increase of circuit design spaces and the computational cost of iterative …
Page 1 of 4