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 32 for “"Exploration-Exploitation Trade-off"”.

  1. Exploration-Exploitation Trade-Off in Reinforcement Learning

    The exploration-exploitation trade-off is a fundamental challenge in reinforcement learning. Recent applications of reinforcement learning in large language models and world models have further underscored the critical need for principled, scalable, and efficient exploration algorithms. Exploration …

    tamu Repository record for Exploration-Exploitation Trade-Off in Reinforcement Learning (opens in a new tab)

  2. Exploration-Exploitation Trade-Off in Reinforcement Learning

    The exploration-exploitation trade-off is a fundamental challenge in reinforcement learning. Recent applications of reinforcement learning in large language models and world models have further underscored the critical need for principled, scalable, and efficient exploration algorithms. Exploration …

    tamu Repository record for Exploration-Exploitation Trade-Off in Reinforcement Learning (opens in a new tab)

  3. The exploration-exploitation trade-off in sequential decision making problems

    … of actions. Common to such problems is the exploration-exploitation trade-off, where an agent must choose between the action expected to yield the best reward (exploitation) or trying an alternative action for potential future benefit (exploration). The main focus of this thesis is to …

    lancaster Download PDF for The exploration-exploitation trade-off in sequential decision making problems (opens in a new tab)

  4. Learning and earning under uncertainty: The impact of uncertainty on human choice and attention in the exploration/exploitation trade-off.

    The exploration/exploitation trade-off (EE trade-off) describes how, when faced with multiple competing alternatives, a decision-maker must often choose between using their current knowledge to gain rewards (exploitation), and trying out new alternatives to gain information (exploration). Recent …

    unsw Repository record for Learning and earning under uncertainty: The impact of uncertainty on human choice and attention in the exploration/exploitation trade-off. (opens in a new tab)

  5. Evolutionary Policy Optimization

    … in reinforcement learning (RL) is managing the exploration-exploitation trade-off without sacrificing sample efficiency. Policy gradient (PG) methods excel in exploitation through fine-grained, gradient-based optimization but often struggle with exploration due to their focus on local search. In …

    texas Repository record for Evolutionary Policy Optimization (opens in a new tab)

  6. Budget-constrained Bayesian optimization

    … function, which must effectively balance exploration and exploitation to converge quickly. Default acquisition functions such as expected improvement are greedy in the sense that they ignore how the current iteration will affect future ones. Typically, the BO exploration-exploitation …

    cornell Repository record for Budget-constrained Bayesian optimization (opens in a new tab)

  7. NEW ADVANCES ON BAYESIAN AND DECISION-THEORETIC APPROACHES FOR INTERACTIVE MACHINE LEARNING

    THE EXPLORATION-EXPLOITATION TRADE-OFF IS A FUNDAMENTAL DILEMMA IN MANY INTERACTIVE LEARNING SCENARIOS, WHICH INCLUDE BOTH ASPECTS OF REINFORCEMENT LEARNING (RL) AND ACTIVE LEARNING (AL). MORE OFTEN, LEARNING STRATEGIES THAT IGNORE EXPLORATION WILL EXHIBIT SUB-OPTIMAL PERFORMANCE WHILE, CONVERSELY, …

    nus Repository record for NEW ADVANCES ON BAYESIAN AND DECISION-THEORETIC APPROACHES FOR INTERACTIVE MACHINE LEARNING (opens in a new tab) Download file for NEW ADVANCES ON BAYESIAN AND DECISION-THEORETIC APPROACHES FOR INTERACTIVE MACHINE LEARNING (opens in a new tab)

  8. THREE ESSAYS IN MODERN PORTFOLIO THEORY

    … framework in mean-variance problem provides an exploration-exploitation trade-off mechanism; if we additionally consider model misspecification, robust strategy essentially weights more on exploitation rather than exploration and thus reflects a more conservative optimization scheme.

    nus Repository record for THREE ESSAYS IN MODERN PORTFOLIO THEORY (opens in a new tab) Download file for THREE ESSAYS IN MODERN PORTFOLIO THEORY (opens in a new tab)

  9. Prefrontal Brain Microstructural Integrity is Related to an Exploitation Bias in Older Adulthood

    The exploration–exploitation trade-off reflects a fundamental decision-making process supported by interactions between cortical regions involved in reward valuation and monitoring and subcortical systems that regulate attention and learning. In previous work, we demonstrated that microstructural …

    york Repository record for Prefrontal Brain Microstructural Integrity is Related to an Exploitation Bias in Older Adulthood (opens in a new tab)

  10. Combining Experimental and Theoretical Evidence to Understand Predator Learning Behaviour with Unfamiliar Prey

    … that formalized prey selection in terms of an exploration-exploitation trade-off. Here, I identified the optimal sampling strategy for a predator with Bayesian learning. I demonstrate that a predator's prior beliefs (Bayesian priors), and the certainty it has in its beliefs affect the optimal …

    carleton Repository record for Combining Experimental and Theoretical Evidence to Understand Predator Learning Behaviour with Unfamiliar Prey (opens in a new tab)

  11. Interactive Music Recommendation: Context,Content and Collaborative Filtering

    … to music recommendation by formulating the exploration-exploitation trade-off in music recommendation as an interactive reinforcement learning task. Extensive evaluations are conducted to demonstrate the effectiveness of the developed methods. Third, we developed a model that simultaneously …

    nus Repository record for Interactive Music Recommendation: Context,Content and Collaborative Filtering (opens in a new tab) Download file for Interactive Music Recommendation: Context,Content and Collaborative Filtering (opens in a new tab)

  12. Reliable and efficient post-training of large reasoning models : reinforcement learning dynamics and adaptation

    … as a token-level quantity for steering the exploration-exploitation trade-off, and provides a unified policy-gradient view connecting direct Pass@K optimization, advantage shaping, and related surrogate objectives. The second part studies efficient adaptation across the broader post-training …

    ubc Repository record for Reliable and efficient post-training of large reasoning models : reinforcement learning dynamics and adaptation (opens in a new tab) Download PDF for Reliable and efficient post-training of large reasoning models : reinforcement learning dynamics and adaptation (opens in a new tab)

  13. Quantum inspired algorithms for learning and control of stochastic systems

    … reinforcement learning techniques is the exploration-exploitation trade-off. To address the above issue an action selection procedure inspired by a quantum search algorithm called Grover's iteration is developed. This procedure does not require an explicit design parameter to specify the …

    must-thes Repository record for Quantum inspired algorithms for learning and control of stochastic systems (opens in a new tab)

  14. Robust and personalised online learning

    … the bandit framework effectively tackles the exploration-exploitation trade-off by modelling sequential decision making problems in a mathematically tractable manner. Meanwhile, the rapid growth of data through smartphones, edge devices, and networked sensors has created an urgent need for …

    lancaster Download PDF for Robust and personalised online learning (opens in a new tab)

  15. Statistical inference for periodic and partially observable poisson processes

    … develops practical Bayesian estimators and exploration methods for count data collected by autonomous robots with unreliable sensors for long periods of time. It addresses the problems of drawing inferences from temporally incomplete and unreliable count data. This thesis contributes …

    birmingham Download PDF for Statistical inference for periodic and partially observable poisson processes (opens in a new tab)

  16. Exploration Versus Exploitation Decisions in the Human Brain: A Systematic Review of Functional Neuroimaging and Neuropsychological Studies

    … Yet, the neural mechanisms underlying this exploration-exploitation trade-off in humans remain poorly understood. This is attributable to variability in the operationalization of exploration and exploitation as psychological constructs, the heterogeneity of experimental protocols and …

    york Repository record for Exploration Versus Exploitation Decisions in the Human Brain: A Systematic Review of Functional Neuroimaging and Neuropsychological Studies (opens in a new tab)

  17. ONLINE RESOURCE ALLOCATION AND ITS APPLICATIONS

    … MAB is a classical problem that exemplifies the exploration-exploitation trade-off. Standard formulations of MAB do not take into account risk. In online decision-making systems, risk is a primary concern. In this regard, the mean-variance and CVaR risk measures are the most common objective …

    nus Repository record for ONLINE RESOURCE ALLOCATION AND ITS APPLICATIONS (opens in a new tab) Download file for ONLINE RESOURCE ALLOCATION AND ITS APPLICATIONS (opens in a new tab)

  18. Contextual Bandits With Delayed Feedback Using Randomized Allocation

    … practical settings that require balancing the exploration-exploitation trade-off to maximize total rewards. Motivated by applications in health care, we consider a multi-armed bandit setting with covariates and allow for delay in observing the rewards (treatment outcomes) as would most likely …

    umn Repository record for Contextual Bandits With Delayed Feedback Using Randomized Allocation (opens in a new tab)

  19. An artificial experimenter for automated response characterisation

    … and a Bayesian surprise method for managing the exploration{exploitation trade-off between new feature discovery and hypothesis disproving. The techniques are validated through a laboratory trial where successful biological characterisation has been shown

    soton Download PDF for An artificial experimenter for automated response characterisation (opens in a new tab)

  20. Learning-Based Controller Design with Application to a Chiller Process

    … the system. This is referred to as the exploration-exploitation trade-off. Although optimal dual controllers in theory can be computed by solving a functional equation, this is usually intractable in practice, with only some simple special cases as exceptions. Therefore, it is …

    lund Repository record for Learning-Based Controller Design with Application to a Chiller Process (opens in a new tab) Download PDF for Learning-Based Controller Design with Application to a Chiller Process (opens in a new tab)

Page 1 of 2