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 401 for “"Markov Decision Processes"”.

  1. Spectrum Management using Markov Decision Processes

    … use, with a focus on combining multiple control decisions in a mutually beneficial manner. Our approach to making spectrum management decisions is grounded in Markov decision theory, which has a rich formal foundation and is frequently used to guide decision making in other disciplines. Here, we …

    wustl Repository record for Spectrum Management using Markov Decision Processes (opens in a new tab)

  2. Risk management by Markov decision processes

    … including risk management is the model of Markov decision processes. My PhD research in the area of risk management is focused on three major problems: (1) risk sensitive partially observable Markov decision processes, (2) dynamic risk measures, (3) dynamic deviation measures. Our first …

    manitoba Repository record for Risk management by Markov decision processes (opens in a new tab)

  3. LEARNING ALGORITHMS FOR MARKOV DECISION PROCESSES

    … schemes for solving Partially Observable Markov Decision Processes with the finite stage additive cost and infinite horizon discounted cost criterion. Error bounds for the corresponding algorithms are given and it is further shown that at the expense of more computational effort the …

    maryland Repository record for LEARNING ALGORITHMS FOR MARKOV DECISION PROCESSES (opens in a new tab)

  4. Topics in Online Markov Decision Processes

    <p>This dissertation describes sequential decision making problems in non-stationary environments. Online learning algorithms deal with non-stationary environments, but generally there is no notion of a dynamic state to model future impacts of past actions. State-based models are common in …

    duke Repository record for Topics in Online Markov Decision Processes (opens in a new tab)

  5. Markov Decision Processes with Information Costs

    For several decades, the theory of Markov decision processes has been successfully used to model situations of controlled stochastic dynamics in various application areas. Beside the original setting which assumes the controlled process to be completely observable at all times, there exist several …

    fu-berlin Repository record for Markov Decision Processes with Information Costs (opens in a new tab)

  6. Algorithms for partially observable Markov decision processes

    … discrete-time finite-state partially observable Markov decision processes. For the infinite horizon problem, only discounted reward case is considered. Several new algorithms for the finite horizon and the infinite horizon problems are developed. For the finite horizon problem, two new algorithms …

    ubc Repository record for Algorithms for partially observable Markov decision processes (opens in a new tab) Download PDF for Algorithms for partially observable Markov decision processes (opens in a new tab)

  7. Linear Approximations For Factored Markov Decision Processes

    A Markov Decision Process (MDP) is a model employed to describe problems in which a decision must be made at each one of several stages, while receiving feedback from the environment. This type of model has been extensively studied in the operations research community and fundamental algorithms …

    waterloo Repository record for Linear Approximations For Factored Markov Decision Processes (opens in a new tab)

  8. Learning in Partially Observable Markov Decision Processes

    Learning in Partially Observable Markov Decision process (POMDP) is motivated by the essential need to address a number of realistic problems. A number of methods exist for learning in POMDPs, but learning with limited amount of information about the model of POMDP remains a highly anticipated …

    iupui Repository record for Learning in Partially Observable Markov Decision Processes (opens in a new tab)

  9. Structural Results for Constrained Markov Decision Processes

    … on the dynamic control of service systems, a decision-maker seeks to optimize a single performance metric over a given time-horizon. However, in many settings, the decision-maker may be interested in multiple performance metrics. Take, for instance, the problem of assigning cross-trained …

    cornell Repository record for Structural Results for Constrained Markov Decision Processes (opens in a new tab)

  10. Sport-Strategy Optimization with Markov Decision Processes

    … games increases, the need for a data-driven decision support increases, too. Especially if opposing effects need to be weighed up, a data-driven approach can uncover insights that are not available from a solely qualitative analysis. The underlying mathematical framework used in this thesis …

    bayreuth Repository record for Sport-Strategy Optimization with Markov Decision Processes (opens in a new tab)

  11. Active Sensing for Partially Observable Markov Decision Processes

    … a model for active sensor selection within decision-making processes, in which observational features are selected based on longer-term impact on the decisions made by the smart phone. This thesis formulates the problem as a partially observable Markov decision process (POMDP), and proposes …

    waterloo Repository record for Active Sensing for Partially Observable Markov Decision Processes (opens in a new tab)

  12. Regret-based Reward Elicitation for Markov Decision Processes

    Markov decision processes (MDPs) have proven to be a useful model for sequential decision- theoretic reasoning under uncertainty, yet they require the specification of a reward function that can require sophisticated human judgement to assess relevant tradeoffs. This dissertation casts the problem …

    toronto-retro Repository record for Regret-based Reward Elicitation for Markov Decision Processes (opens in a new tab)

  13. Acceleration of Iterative Methods for Markov Decision Processes

    This research focuses on Markov Decision Processes (MDP). MDP is one of the most important and challenging areas of Operations Research. Every day people make many decisions: today's decisions impact tomorrow's and tomorrow's will impact the ones made the day after. Problems in Engineering, …

    toronto-retro Repository record for Acceleration of Iterative Methods for Markov Decision Processes (opens in a new tab)

  14. Quasi-Random Action Selection In Markov Decision Processes

    In Markov decision processes an operator exploits known data regarding the environment it inhabits. The information exploited is learned from random exploration of the state-action space. This paper proposes to optimize exploration through the implementation of quasi-random sequences in both …

    gsu Repository record for Quasi-Random Action Selection In Markov Decision Processes (opens in a new tab)

  15. Experimental Design For Partially Observed Markov Decision Processes

    … conduct experiments in Partially Observed Markov Decision Processes so as to provide data that is most informative about a parameter of interest. Methods from Markov decision processes, especially dynamic programming, are introduced and then used in algorithms to maximize a relevant Fisher …

    cornell Repository record for Experimental Design For Partially Observed Markov Decision Processes (opens in a new tab)

  16. Bayesian Reinforcement Learning on Semi–Markov Decision Processes

    Automated decision making is a highly relevant research topic in the context of supply chains as the usage of automated vehicles is increasing. Further, utilising historical data and domain knowledge to increase the performance and ensure robust behaviour of the decision–making agent is valuable …

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

  17. Statistical Model Checking with Robust Markov Decision Processes

    … system with non-deterministic choices modeled by Markov decision processes (MDP), for which a confidence region is given in the form of a robust MDP (RMDP). For this task, we introduce a compositional framework for model-based SMC with PAC guarantees, consisting of three sub-problems: sampling the …

    qucosa-diss

  18. Policy-Gradient Algorithms for Partially Observable Markov Decision Processes

    Partially observable Markov decision processes are interesting because of their ability to model most conceivable real-world learning problems, for example, robot navigation, driving a car, speech recognition, stock trading, and playing games. The downside of this generality is that exact …

    anu Repository record for Policy-Gradient Algorithms for Partially Observable Markov Decision Processes (opens in a new tab)

Page 1 of 21