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 18 of 18 for “"Model-free Reinforcement Learning"”.

  1. Information-theoretic Algorithms for Model-free Reinforcement Learning

    In this work, we propose a model-free reinforcement learning algorithm for infinte-horizon, average-reward decision processes where the transition function has a finite yet unknown dependence on history, and where the induced Markov Decision Process is assumed to be weakly communicating. This …

    mit Repository record for Information-theoretic Algorithms for Model-free Reinforcement Learning (opens in a new tab)

  2. Model-free reinforcement learning in non-stationary Markov Decision Processes

    Reinforcement learning (RL) studies the problem where an agent maximizes its cumulative reward through sequential interactions with an initially unknown environment, usually modeled by a Markov Decision Process (MDP). The classical RL literature typically assumes that the state transition functions …

    uiuc Repository record for Model-free reinforcement learning in non-stationary Markov Decision Processes (opens in a new tab)

  3. Efficient Bayesian Nonparametric Methods for Model-Free Reinforcement Learning in Centralized and Decentralized Sequential Environments

    … are increasing demands for designing efficient learning algorithms for these agents to improve their control polices. Such policies must account for uncertainties, including those caused by environmental stochasticity, sensor noise and communication restrictions. These challenges exist in …

    duke Repository record for Efficient Bayesian Nonparametric Methods for Model-Free Reinforcement Learning in Centralized and Decentralized Sequential Environments (opens in a new tab)

  4. An Application of Sliding Mode Control to Model-Based Reinforcement Learning

    <p>The state-of-art model-free reinforcement learning algorithms can generate admissible controls for complicated systems with no prior knowledge of the system dynamics, so long as sufficient (oftentimes millions) of samples are available from the environ- ment. On the other hand, model-based …

    calpoly Repository record for An Application of Sliding Mode Control to Model-Based Reinforcement Learning (opens in a new tab)

  5. Tame Long-Horizon Model-Based Reinforcement Learning

    Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across tasks. Model-based RL, on the other hand, learns task-agnostic …

    mit Repository record for Tame Long-Horizon Model-Based Reinforcement Learning (opens in a new tab)

  6. Selecting appropriate reinforcement-learning algorithms for robot manipulation domains

    Engineering reinforcement learning agents for application on a particular target domain requires making decisions such as the learning algorithm and state representation. We empirically study the performance of three reference implementations of model-free reinforcement learning algorithms: …

    mit Repository record for Selecting appropriate reinforcement-learning algorithms for robot manipulation domains (opens in a new tab)

  7. Motor learning on a heaving plate via improved-SNR algorithms

    … as yet unmatched by engineered solutions. Model-free reinforcement learning (MFRL) holds the promise of allowing man-made controllers to take advantage of the subtlety of fluid-body interactions solely using data gathered on the actual system to be controlled. In this thesis, improved MFRL …

    mit Repository record for Motor learning on a heaving plate via improved-SNR algorithms (opens in a new tab)

  8. Residual Model Learning for Microrobot Control

    … using compliant materials that are difficult to model analytically, limiting the utility of traditional model-based controllers. Challenges in data collection on microrobots and large errors between simulated models and real robots make current model-based learning and sim-to-real transfer …

    mit Repository record for Residual Model Learning for Microrobot Control (opens in a new tab)

  9. Sample-efficient reinforcement learning

    Reinforcement learning has been instrumental in the recent advances made by artificial intelligence agents in various domains. Most of these advances have been abetted by the availability of huge amounts of training data. But, in several practical applications such as those arising in wireless …

    uiuc Repository record for Sample-efficient reinforcement learning (opens in a new tab)

  10. Topics in Dynamic programming and Economic Networks

    … among a multitude of diverse agents. The network models provide a comprehensive analysis of how individual agent behaviours, incentives, and strategic interactions contribute to the larger systemic forces or shocks within aggregate economics. This thesis addresses problems in dynamic programming …

    aus-cath Repository record for Topics in Dynamic programming and Economic Networks (opens in a new tab)

  11. Topics in Dynamic programming and Economic Networks

    … among a multitude of diverse agents. The network models provide a comprehensive analysis of how individual agent behaviours, incentives, and strategic interactions contribute to the larger systemic forces or shocks within aggregate economics. This thesis addresses problems in dynamic programming …

    anu Repository record for Topics in Dynamic programming and Economic Networks (opens in a new tab)

  12. Active Inference in Multi-Objective Dynamic Environments

    … done to explore the framework's viability in modelling scenarios both related to neural process theory and more classical agent-based machine learning. However, due to the relative recency of the theory, there are still many areas of comparison and evaluation to explore. This dissertation aims …

    cape-town Repository record for Active Inference in Multi-Objective Dynamic Environments (opens in a new tab)

  13. Theoretical and Experimental Investigation of Free-Floating Space Manipulator Motion Control Using Reinforcement Learning

    … the critical motion planning problem for a 6DOF free-floating space manipulator using model-free Reinforcement Learning. This problem is caused by dynamic coupling between the spacecraft and robotic manipulator, which significantly affects control and precision in the space environment. This …

    york Repository record for Theoretical and Experimental Investigation of Free-Floating Space Manipulator Motion Control Using Reinforcement Learning (opens in a new tab)

  14. Simultaneous activation of multiple memory systems during learning : insights from electrophysiology and modeling

    … and how their neural activities evolve during learning. To address these issues, single-unit activity was recorded simultaneously in dorsolateral (sensorimotor) and dorsomedial (associative) regions of the striatum as rats learned two versions of a conditional T-maze task. The results …

    mit Repository record for Simultaneous activation of multiple memory systems during learning : insights from electrophysiology and modeling (opens in a new tab)

  15. Improving Exploration in Reinforcement Learning through Domain Knowledge and Parameter Analysis

    … novel work on how to improve exploration in reinforcement learning using domain knowledge and knowledge-based approaches to reinforcement learning. It also identifies novel relationships between the algorithms' and domains' parameters and the exploration efficiency. The goal of solving …

    whiterose Repository record for Improving Exploration in Reinforcement Learning through Domain Knowledge and Parameter Analysis (opens in a new tab)

  16. Sample-Efficient Deep Reinforcement Learning for Continuous Control

    Reinforcement learning (RL) is a powerful, generic approach to discovering optimal policies in complex sequential decision-making problems. Recently, with flexible function approximators such as neural networks, RL has greatly expanded its realm of applications, from playing computer games with …

    cambridge Repository record for Sample-Efficient Deep Reinforcement Learning for Continuous Control (opens in a new tab)

  17. Statistical problems with deterministic reinforcement learning and small sample biases

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms

    uiuc Repository record for Statistical problems with deterministic reinforcement learning and small sample biases (opens in a new tab)