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 14 of 14 for “"Bayesian Reinforcement Learning"”.

  1. Sparse Bayesian reinforcement learning

    … and retention methods for efficient and robust learning. We propose a framework for learning and memorizing, and we examine how we can use the memory for efficient machine learning. Temporal difference (TD) learning is a core part of reinforcement learning, and it requires function …

    colostate Repository record for Sparse Bayesian reinforcement learning (opens in a new tab)

  2. Scalable Bayesian Reinforcement Learning

    … environments. We formulate this problem as Bayesian Reinforcement Learning (BRL) over latent Markov Decision Processes (MDPs). While Bayes-optimality is theoretically the gold standard, existing algorithms scale poorly to continuous state and action spaces. This thesis proposes a set of BRL …

    washington Repository record for Scalable Bayesian Reinforcement Learning (opens in a new tab)

  3. Offline Policy-search in Bayesian Reinforcement Learning

    … research contributions in the study field of Bayesian Reinforcement Learning — a subfield of Reinforcement Learning where, even though the dynamics of the system are un- known, the existence of some prior knowledge is assumed in the form of a distribution over Markov decision processes. In …

    liege Repository record for Offline Policy-search in Bayesian Reinforcement Learning (opens in a new tab) Download PDF for Offline Policy-search in Bayesian Reinforcement Learning (opens in a new tab)

  4. Bayesian Reinforcement Learning on Semi–Markov Decision Processes

    … process (SMDP) is an extension of the, in reinforcement learning commonly used, Markov decision process (MDP), that allows for modelling systems with stochastic state and time transition dynamics. In Bayesian reinforcement learning, ideas from Bayesian statistics are incorporated with …

    chalmers Repository record for Bayesian Reinforcement Learning on Semi–Markov Decision Processes (opens in a new tab)

  5. Analysis of New Methods for Inference in Markov Decision Processes

    … for computing statistics for value functions in Bayesian reinforcement learning. This involves investigating a recently developed mean field theory and its relationship with expectations of maxima of sets of random variables. The objective is to precisely calculate the mean of posterior optimal …

    adelaide Repository record for Analysis of New Methods for Inference in Markov Decision Processes (opens in a new tab)

  6. Machine learning for intelligent agents

    … components, and adapt its behaviour through learning. In this direction, the present dissertation concerns the development, implementation and evaluation of machine learning techniques for building intelligent agents. Three important and very challenging tasks are considered: i) approximate …

    greece Repository record for Machine learning for intelligent agents (opens in a new tab)

  7. Challenges in Continuous Path Planning: Rarefactions, Uncertainty and Reinforcement Learning

    … The third section considers an online-learning path-planning problem with unknown surveillance intensity and develops a Bayesian reinforcement learning method. In addition to the three path-planning problems, a new method of parameterizing neural networks is introduced. It follows the …

    cornell Repository record for Challenges in Continuous Path Planning: Rarefactions, Uncertainty and Reinforcement Learning (opens in a new tab)

  8. A Surrogate-Assisted Online Adaptive Reinforcement Learning and Approximate Bayesian Computation (OARL-ABC) Method for Calibration of Digital Twins

    … a new surrogate model assisted online adaptive reinforcement learning and approximate Bayesian computation (OARL-ABC) method for the calibration and validation of digital twins. The approach builds upon a reinforcement learning-based calibration framework that performs model selection via …

    gatech Repository record for A Surrogate-Assisted Online Adaptive Reinforcement Learning and Approximate Bayesian Computation (OARL-ABC) Method for Calibration of Digital Twins (opens in a new tab)

  9. Cost and Power Loss Aware Coalitions under Uncertainty in Transactive Energy Systems

    … game theory techniques empowered with machine learning methods across grid infrastructure and microgrid communities. In this thesis, novel Bayesian coalitional game theory-based and Bayesian reinforcement learning-based coalition formation algorithms are proposed, which allow the microgrids to …

    ottawa-retro Repository record for Cost and Power Loss Aware Coalitions under Uncertainty in Transactive Energy Systems (opens in a new tab)

  10. Control-Aware Distributed Channel Access for Networked Control Systems

    … consider scenarios that necessitate the use of learning methods to evaluate transmission priorities and address how the learning can be done in a distributed way without compromising control performance. Data transmission in certain industrial environments is prone to correlated packet dropouts, …

    aalto Repository record for Control-Aware Distributed Channel Access for Networked Control Systems (opens in a new tab)

  11. Addressing Uncertainty in Cyber-Physical Power Systems - Modeling to Integration in a Cyber-Physical Energy Management System

    … the conventional supervised and semi-supervised learning techniques. But a major limitation of this approach is that it does not easily support utilization of the existing domain knowledge. Hence, a Bayesian Approach is undertaken for inferencing and learning the structure of a novel cyber attack …

    tamu Repository record for Addressing Uncertainty in Cyber-Physical Power Systems - Modeling to Integration in a Cyber-Physical Energy Management System (opens in a new tab)

  12. Medical decision support for treating infectious diseases

    With an ever increasing digitalization of health care and records thereof, possibilities of applying data driven methods to analyze and predict healthcare outcomes are becoming more numerous. Markov decision processes (MDPs) are an interesting class of models to explore in this context. Originally …

    chalmers Repository record for Medical decision support for treating infectious diseases (opens in a new tab)

  13. Optimal Learning Theory and Approximate Optimal Learning Algorithms

    … but often computationally intractable problem in reinforcement learning. The dilemma also impacts data efficiency which can be pivotal when the interactions between the agent and the environment are constrained. Traditional optimal control theory has some notion of objective criterion, such as …

    waterloo Repository record for Optimal Learning Theory and Approximate Optimal Learning Algorithms (opens in a new tab)

  14. Ensembling and Coordination Methods for Sequential Decision Making Under Uncertainty

    … and using policy improvement techniques from reinforcement learning to achieve policy improvement results. We provide numerous Bayesian and frequentist characterization of performance. As part of implementing our proposed algorithms, we proposes and prove consistency for a novel inverse …

    duke Repository record for Ensembling and Coordination Methods for Sequential Decision Making Under Uncertainty (opens in a new tab)