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 19 of 19 for “"Multi-Objective Reinforcement Learning"”.

  1. Intrinsically motivated multi-objective reinforcement learning

    … decision-making processes in which the learning agent senses the world's state, evaluates the expected value for different actions, takes the action that can maximize this value, and observes the real outcome of the taken action. Over the last decade, reinforcement learning methods …

    unsw Repository record for Intrinsically motivated multi-objective reinforcement learning (opens in a new tab)

  2. Meta multi-objective reinforcement learning for communication load balancing

    … neighboring ones. In this thesis, we study multi-objective reinforcement learning (MORL) and meta reinforcement learning (meta-RL) for load balancing to learn highly customized policies for different trade-offs between network performance metrics. We begin with a thorough review of existing …

    manitoba Repository record for Meta multi-objective reinforcement learning for communication load balancing (opens in a new tab)

  3. Multi-Objective Reinforcement Learning Framework for Unknown Stochastic & Uncertain Environments

    … on the problem of uncertainty handling during learning, by agents dealing in stochastic environments by means of Multi Objective Reinforcement Learning (MORL). Most previous investigations into multi objective reinforcement learning have proposed algorithms to deal with the learning performance …

    salford Repository record for Multi-Objective Reinforcement Learning Framework for Unknown Stochastic & Uncertain Environments (opens in a new tab) Download PDF for Multi-Objective Reinforcement Learning Framework for Unknown Stochastic & Uncertain Environments (opens in a new tab)

  4. Sample-efficient multi-task and multi-objective reinforcement learning by combining multiple behaviors

    … in the field of artificial intelligence, and reinforcement learning (RL) in particular, is the development of generalist and flexible agents that are capable of solving multiple tasks—each requiring the agent to learn a potentially new, specialized behavior. Importantly, tackling this …

    brazil-ufrgs Repository record for Sample-efficient multi-task and multi-objective reinforcement learning by combining multiple behaviors (opens in a new tab)

  5. Multi-objective reinforcement learning methods for action selection : dealing with multiple objectives and non-stationarity

    Multi-objective decision-making entails planning based on a model to find the best policy to solve such problems. If this model is unknown, learning through interaction provides the means to behave in the environment. Multi-objective decision-making in a multi-agent system poses many unsolved …

    brazil-ufrgs Repository record for Multi-objective reinforcement learning methods for action selection : dealing with multiple objectives and non-stationarity (opens in a new tab)

  6. Improving lookahead assembly scheduling in modular building projects using linked data-based space constraint checking and multi-objective reinforcement learning

    … adequately. Third, little research has examined multi-objective optimization and Pareto-front generation for lookahead assembly schedules. Addressing these gaps, this research first proposed a linked data-based framework for detecting space constraint violations in lookahead assembly schedules …

    auckland-ms Repository record for Improving lookahead assembly scheduling in modular building projects using linked data-based space constraint checking and multi-objective reinforcement learning (opens in a new tab)

  7. Autonomous Driving: A Multi-Objective Deep Reinforcement Learning Approach

    … driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers. It's representative of complex reinforcement learning tasks humans …

    waterloo Repository record for Autonomous Driving: A Multi-Objective Deep Reinforcement Learning Approach (opens in a new tab)

  8. Deep Q-Managed: a new framework fror Multi-Objective Deep Reinforcement Learning

    … a significant advancement in the field of multi-objective reinforcement learning (MORL). This new strategy employs an updated technique for hybrid multi-objective optimization, which offers a mathematical guarantee that all policies belonging to the Pareto Front can be found, excelling in …

    brazil-ufrn Repository record for Deep Q-Managed: a new framework fror Multi-Objective Deep Reinforcement Learning (opens in a new tab)

  9. Pareto conditioned networks in continuous action spaces /

    Reinforcement learning is one of the main paradigms of machine learning methodologies, a technique for sequential decision making in a fully or partially observed environment. The main objective of this approach is to optimise accumulated rewards over time. Generally, these rewards are scalar and …

    vilnius Repository record for Pareto conditioned networks in continuous action spaces / (opens in a new tab)

  10. Προδιαγραφική αναλυτική δεδομένων με διαδραστική ενισχυτική μάθηση στη λήψη αποφάσεων

    … with the data-driven decision making, machine learning algorithms and big data technologies to support complex prescriptive analytics problems of various domains. To that end, it develops a prescriptive analytics framework that can guide the development of various prescriptive methods. These …

    greece Repository record for Προδιαγραφική αναλυτική δεδομένων με διαδραστική ενισχυτική μάθηση στη λήψη αποφάσεων (opens in a new tab)

  11. Socially Normative Mobile Robot Navigation in Construction

    … safely and effectively. The study has three main objectives: (1) identifying implicit proxemic norms that influence human robot spatial interactions in various coexistence scenarios; (2) assessing the impacts of socially normative robot behaviors on human perception and task performance; and (3) …

    gatech Repository record for Socially Normative Mobile Robot Navigation in Construction (opens in a new tab)

  12. Optimization and Learning in Energy Efficient Cognitive Radio System

    … the study is focused on the optimization and learning of energy efficiency in the cognitive radio system, which can be considered to better utilize both the energy and spectrum resources. Firstly, <em>drowsy transmission</em>, which produces optimized idle period patterns and selects the best …

    utk-theses Repository record for Optimization and Learning in Energy Efficient Cognitive Radio System (opens in a new tab)

  13. Reinforcement Learning Applied to Open Pit Mine Haul Truck Dispatch under Stochasticity and Deviations

    … approach. This research implements a suite of reinforcement learning-based dispatching systems for overcoming stochasticity, adapting to non-stationary environments, and handling the conflicting objectives of production and fleet reliability. The first study focuses on general sources of …

    queens Repository record for Reinforcement Learning Applied to Open Pit Mine Haul Truck Dispatch under Stochasticity and Deviations (opens in a new tab)

  14. Scalable Systems for Machine Learning

    Federated Learning (FL) enables collaborative model training without centralized data collection, thereby preserving data privacy and reducing data transfer costs. However, deploying FL in resource-constrained distributed environments like Edge and IoT applications introduces significant challenges …

    vt Repository record for Scalable Systems for Machine Learning (opens in a new tab)

  15. Exploration Strategies for Homeostatic Agents: Continuous and dynamic exploration for homeostatic regulation using deep reinforcement learning

    … homeostatic agents. Homeostatic agents have the objective of keeping some internal variables as close to a predetermined optimum as possible. Reinforcement learning is used for decision making, and the agents are given access to the optimal and acceptable values of the internal variables, giving …

    chalmers Repository record for Exploration Strategies for Homeostatic Agents: Continuous and dynamic exploration for homeostatic regulation using deep reinforcement learning (opens in a new tab)

  16. Information-Theoretic Measures in Selected Learning Problems

    … the usage of information-theoretic measures in learning problems. The first problem considered is the algorithm-dependent generalization error bound. Conceptually, the mutual information between the output of the learning algorithm and training samples captures the amount of information the …

    tamu Repository record for Information-Theoretic Measures in Selected Learning Problems (opens in a new tab)

  17. Towards Efficient Spatial and Textual Query Processing: Learned Indexing and Cardinality Estimation

    … data, where each entity is associated with multiple textual values (e.g., product tags, user interests, or description keywords), is ubiquitous in various modern applications, such as recommendation systems, social networks, and information retrieval. However, because of its high-dimensional …

    unsw Repository record for Towards Efficient Spatial and Textual Query Processing: Learned Indexing and Cardinality Estimation (opens in a new tab)

  18. Learning-Based Multi-Objective Operation of Microgrid with Renewable Uncertainty and Demand-side Management

    … with highly variable weather conditions. Also, multi-objective problems yield a set of optimal trade-off solutions instead of a single one, requiring higher computational complexity. Moreover, the interdependency of supply and demand management problems leads to tighter coupling or numerical …

    rit Repository record for Learning-Based Multi-Objective Operation of Microgrid with Renewable Uncertainty and Demand-side Management (opens in a new tab)