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 119 for “"Human Feedback"”.

  1. Reinforcment learning from human feedback /

    … the exploration of reinforcement learning from human feedback as a solution for general reinforcement learning problems. After a thorough review of the relevant literature, the study compares two distinct reinforcement learning methodologies: traditional reinforcement learning and a variant of …

    vilnius Repository record for Reinforcment learning from human feedback / (opens in a new tab)

  2. Learning with and without human feedback

    Labels and feedback provided by humans play a central role in training contemporary machine learning models, offering models ground truth annotations from which to extract patterns. However, collecting such feedback from humans is a challenging and time-consuming task. As a result, practitioners …

    gatech Repository record for Learning with and without human feedback (opens in a new tab)

  3. Learning from Naturally Occurring Human Feedback

    … have made progress in aligning models with human intent, but they rely on preference data from paid annotators, do not enable continual post-deployment improvement, and still depend on users’ prompt engineering skills. To address these limitations, this thesis develops AI language systems …

    cornell Repository record for Learning from Naturally Occurring Human Feedback (opens in a new tab)

  4. Human Feedback in Statistical Machine Translation

    … Machine Translation (SMT) systems via feedback given by humans on translation quality. The amount of human feedback available to systems is inherently low due to cost and time limitations. One of our goals is to simulate such information by automatically generating pseudo-human …

    whiterose Download PDF for Human Feedback in Statistical Machine Translation (opens in a new tab)

  5. Learning to answer questions from human feedback

    … improve the question answering (QA) model from human feedback. We formulate a contextual bandit learning scenario: human users pose questions to a system, and give feedback to output answers based on the context from which they are taken. Prior work in this setting only considered a simplified …

    texas Repository record for Learning to answer questions from human feedback (opens in a new tab)

  6. Applications of human feedback in Gaussian processes

    … data points. If the new data is provided by a human expert, data that is based on comparisons might be less noisy and unbiased than direct observations. The contributions of this dissertation are mainly methodological. The applicability of the techniques developed in this dissertation is tested …

    aalto Repository record for Applications of human feedback in Gaussian processes (opens in a new tab)

  7. Interactive learning from implicit human feedback : the EMPATHIC framework

    … an abundant, natural source of signal emitted by humans during interactions. An autonomous agent could leverage an interpretation of such implicit human feedback to improve its task performance at no cost to the human, contrasting with traditional agent teaching methods based on demonstrations or …

    texas Repository record for Interactive learning from implicit human feedback : the EMPATHIC framework (opens in a new tab)

  8. ChatHF: Collecting Rich Human Feedback from Real-time Conversations

    … collection and annotation of NLP datasets, and Human-Computer Interaction studies, as demonstrated in case studies on image geolocation and assisting older adults with daily activities.

    gatech Repository record for ChatHF: Collecting Rich Human Feedback from Real-time Conversations (opens in a new tab)

  9. Explaining model decisions and fixing them via human feedback

    … it did, 2. enable knowledge transfer between humans and AI, 3. correct unwanted biases learned by AI models, and 4. encourage human-like reasoning in AI.

    gatech Repository record for Explaining model decisions and fixing them via human feedback (opens in a new tab)

  10. Algorithmic Foundations for Safe and Efficient Reinforcement Learning from Human Feedback

    … function. Instead, Reinforcement Learning from Human Feedback (RLHF) allows RL agents to learn from human-provided data, such as evaluations or rankings of trajectories. In many applications, human feedback is expensive to collect; therefore, learning robust policies from limited data is …

    ethz Repository record for Algorithmic Foundations for Safe and Efficient Reinforcement Learning from Human Feedback (opens in a new tab)

  11. Human-assisted Neural Machine Translation: Harnessing Human Feedback for Machine Translation

    … research on how to improve NMT systems with human feedback. This feedback can take many forms, including interactive-predictive NMT, post-editing of NMT output, and soliciting ratings or corrections of translations for the purposes of online learning. While these approaches are often …

    washington Repository record for Human-assisted Neural Machine Translation: Harnessing Human Feedback for Machine Translation (opens in a new tab)

  12. Utilizing Human Feedback in the Soft Actor-Critic Algorithm for Autonomous Driving

    … solutions to get around this issue is to utilize human feedback. In the first approach of this research, we tested two methods for the purpose of reducing the training time of the Soft Actor-Critic (SAC), using human feedback. First, we pre-trained SAC with Learning from Demonstrations (LfD) to …

    tamu Repository record for Utilizing Human Feedback in the Soft Actor-Critic Algorithm for Autonomous Driving (opens in a new tab)

  13. The BASIL technique: Bias Adaptive Statistical Inference Learning Agents for Learning from Human Feedback

    … a novel approach for learning behaviors using human-provided feedback that is subject to systematic bias. Our method, known as BASIL, models the feedback signal as a combination of a heuristic evaluation of an action's utility and a probabilistically-drawn bias value, characterized by unknown …

    uky-thes Repository record for The BASIL technique: Bias Adaptive Statistical Inference Learning Agents for Learning from Human Feedback (opens in a new tab)

  14. Event graph optimization in RFI text documents using hierarchical reinforcement learning and human feedback

    … study proposes a novel approach that integrates human feedback-augmented reinforcement learning to enhance RCA for the event graphs of text-based RFIs. Our method leverages expert insights as a core component of the HRL loop in optimizing and improving the accuracy and reliability of causal and …

    concordia Download PDF for Event graph optimization in RFI text documents using hierarchical reinforcement learning and human feedback (opens in a new tab)

  15. Improving Data Efficiency and Availability for Alignment

    … likely to click on. Reinforcement learning from human feedback takes ML further by learning a reward model from preference comparisons to improve an LLM's responses, rather than trying to specify good behavior directly. In both of these settings, human feedback is critical to aligning ML systems …

    cornell Repository record for Improving Data Efficiency and Availability for Alignment (opens in a new tab)

  16. Incorporating human and environmental feedback for robust performance in agent domains

    … and complexity low, knowledge transfer from humans to agents becomes essential. Ideally, human users, including those without programming skills (i.e., non-technical users) should be able to teach agents desired behaviors using simple communication methods as quickly and as effortlessly as …

    ttu Repository record for Incorporating human and environmental feedback for robust performance in agent domains (opens in a new tab)

  17. Towards Safe and Robust Reinforcement Learning: Leveraging Multiple Sources of Information

    … approaches: capturing uncertainty, learning from human feedback and offline RL.<br/><br/>Capturing uncertainty is the first step towards achieving safe and robust RL. It tells what is known and what is not known, and we can improve safety by avoiding unknown situations. For our first approach, we …

    bristol Repository record for Towards Safe and Robust Reinforcement Learning: Leveraging Multiple Sources of Information (opens in a new tab) Download PDF for Towards Safe and Robust Reinforcement Learning: Leveraging Multiple Sources of Information (opens in a new tab)

  18. Reinforcement Learning with Finite Time and Sample Guarantees

    … reward learning from demonstrations and human feedback, establishing finite-sample guarantees for reward estimation. I first present a single-loop regularized Q-learning algorithm for minimizing the projected Bellman error with finite time convergence guarantees in the case of linear …

    tamu Repository record for Reinforcement Learning with Finite Time and Sample Guarantees (opens in a new tab)

  19. Integrating answer set programming and POMDPs for knowledge representation and reasoning in robotics

    … process all sensor inputs, operate without any human input and have possibly-relevant domain knowledge in advance. At the same time, robots cannot be equipped with all relevant domain knowledge in advance, and humans are unlikely to have the time and expertise to provide elaborate and accurate …

    ttu Repository record for Integrating answer set programming and POMDPs for knowledge representation and reasoning in robotics (opens in a new tab)

  20. Aligning Language Models Using Multi-Objective Deep Reinforcement Learning

    … techniques is reinforcement learning from human feedback (RLHF). RLHF aims to optimize one objective based on human preferences. However, the cost of high-quality human feedback is enormous. Having all human annotators consistent in their opinions on desirable behaviors is also challenging. …

    brock Repository record for Aligning Language Models Using Multi-Objective Deep Reinforcement Learning (opens in a new tab)

Page 1 of 6