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 102 for “"Off-Policy"”.

  1. Principled Off-Policy Imitation Learning via Boosting

    … of tasks given some expert data. In particular, off-policy imitation learning is particularly nice for practitioners, as it in principle allows the policy to use previously collected data to improve, similar to standard value-based off-policy reinforcement learning algorithms such as Deep Q …

    cornell Repository record for Principled Off-Policy Imitation Learning via Boosting (opens in a new tab)

  2. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    In reinforcement learning (RL), distributional off-policy evaluation (shortly, distributional OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. In this thesis, we aim to provide theoretically grounded distributional OPE …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  3. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    In reinforcement learning (RL), distributional off-policy evaluation (shortly, distributional OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. In this thesis, we aim to provide theoretically grounded distributional OPE …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  4. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    In reinforcement learning (RL), distributional off-policy evaluation (shortly, distributional OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. In this thesis, we aim to provide theoretically grounded distributional OPE …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  5. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    In reinforcement learning (RL), distributional off-policy evaluation (shortly, distributional OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. In this thesis, we aim to provide theoretically grounded distributional OPE …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  6. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    In reinforcement learning (RL), distributional off-policy evaluation (shortly, distributional OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. In this thesis, we aim to provide theoretically grounded distributional OPE …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  7. Advancing Distributional Off-policy Evaluation in Reinforcement Learning

    In reinforcement learning (RL), distributional off-policy evaluation (shortly, distributional OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. In this thesis, we aim to provide theoretically grounded distributional OPE …

    tamu Repository record for Advancing Distributional Off-policy Evaluation in Reinforcement Learning (opens in a new tab) Embargoed until 2027-08-01

  8. Off-policy Evaluation and Learning for Interactive Systems

    … data from prior versions of the system (a.k.a. off-policy evaluation and learning). While such data is collected in large quantity as a byproduct of system operation, reasoning them is difficult since the data is biased and partial in nature. We present our key contributions in off-policy …

    cornell Repository record for Off-policy Evaluation and Learning for Interactive Systems (opens in a new tab)

  9. Off-policy vyhodnocovanie a učenie v adaptívnych systémoch

    Offline učenie a vyhodnocovanie pre kontextové, mnohoruké bandit algoritmy je vysoko požadované riešenie na zlepšenie adaptívnych webových systémov, pretože proces môže byť spustený \emph{offline}, teda bez priamej interakcie s používateľmi, čím sa zabráni nasadení suboptimálnych algoritmov. …

    brno-tech Repository record for Off-policy vyhodnocovanie a učenie v adaptívnych systémoch (opens in a new tab)

  10. Data efficient reinforcement learning with off-policy and simulated data

    … collected with past behaviors (known as off-policy data) and to allow algorithms to make better use of simulated data sources. This dissertation investigates the use of such auxiliary data by answering the question, "How can a reinforcement learning agent leverage off-policy and simulated …

    texas Repository record for Data efficient reinforcement learning with off-policy and simulated data (opens in a new tab)

  11. Off-Policy Temporal Difference Learning For Robotics And Autonomous Systems

    … with several other applications. Particularly, off-policy temporal difference (TD) learning, a specific type of RL technique, has been widely used in a variety of autonomous tasks. However, there remain significant challenges that must be overcome before it can be successfully applied to various …

    penn Repository record for Off-Policy Temporal Difference Learning For Robotics And Autonomous Systems (opens in a new tab)

  12. Benchmarking Reinforcement Learning and Off Policy Evaluation for Medical Decision Making

    … this benchmark to test seven state-of-the-art offline RL models as well as five common off-policy evaluation (OPE) techniques. My results suggest that while offline RL may be capable of improving upon existing standards of care given large data availability, its applicability does not appear to …

    rockefeller Repository record for Benchmarking Reinforcement Learning and Off Policy Evaluation for Medical Decision Making (opens in a new tab)

  13. Efficient and safe off-policy evaluation : from point estimation to interval estimation

    Offline reinforcement learning involves training a decision-making agent based solely on historical data, without any online interaction with the real-world environment. This data-driven approach is particularly relevant in high-stakes applications, such as medical treatment and robotics, where …

    texas Repository record for Efficient and safe off-policy evaluation : from point estimation to interval estimation (opens in a new tab)

  14. Sample and time efficient strategies for off-policy reinforcement learning in robotic manipulation tasks

    … exploration to find an appropriate control policy capable of solving the robotic manipulation tasks targeted, and, consequently, this sample inefficiency leads to training time inefficiency. The work presented in this thesis aims to solve this problem through three main methods: (i) reward …

    dcu Download PDF for Sample and time efficient strategies for off-policy reinforcement learning in robotic manipulation tasks (opens in a new tab)

  15. Policy Learning and Off-Policy Evaluation with Application to the Sequential Treatment of Rheumatoid Arthritis

    … treatment decision patterns and propose a target policy tailored to individual patient needs. Our approach integrates features derived from patient history, treatment patterns, and clinical characteristics to enhance prediction accuracy. We introduce a novel two-stage combined model that first …

    chalmers Repository record for Policy Learning and Off-Policy Evaluation with Application to the Sequential Treatment of Rheumatoid Arthritis (opens in a new tab)

  16. Methodological contributions to off-policy evaluation under the sample weighting framework and empirical financial analysis using semiparametric machine learning

    … theme advances methodological frameworks in off-policy evaluation for reinforcement learning. Addressing challenges posed by data derived from historical policies, I refine the debiased calibration weighting approach to produce estimators exhibiting semiparametric efficiency and double …

    iastate Repository record for Methodological contributions to off-policy evaluation under the sample weighting framework and empirical financial analysis using semiparametric machine learning (opens in a new tab)

  17. Offline reinforcement learning via an optimization lens

    … and frameworks to address challenges in offline reinforcement learning. More specifically, four perspectives have been studied to improve the efficiency and reliability of offline policy evaluation and learning: 1) We manage to improve the accuracy of off-policy policy evaluation, by …

    texas Repository record for Offline reinforcement learning via an optimization lens (opens in a new tab)

Page 1 of 6