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 210 for “"reinforcement learning (RL)"”.

  1. Developing a generalized intelligent agent by processing information on webpages

    … I designed and implemented a framework for reinforcement learning (RL) agents to interact with a web environment. With this framework, I introduce a new challenge for RL agents to learn human activity on the web. By defining a series of tasks such as using the web as a navigable resource to …

    mit Repository record for Developing a generalized intelligent agent by processing information on webpages (opens in a new tab)

  2. Deploying Reinforcement Learning in the Real World: A Case Study on Apptronik Apollo

    Deep reinforcement learning (RL) has gained increasing popularity as an approach to achieving dynamic behaviors on legged robots. However, transferring RL behaviors from simulation to reality is a challenging process: imperfect sensors, simulation models, control architecture, and latency all …

    vt Repository record for Deploying Reinforcement Learning in the Real World: A Case Study on Apptronik Apollo (opens in a new tab)

  3. Addressing stale gradients in asynchronous federated deep reinforcement learning

    Advancements in reinforcement learning (RL) via deep neural networks have enabled their application to a variety of real-world problems. However, these applications often suffer from long training times. While attempts to distribute training have been successful in controlled scenarios, they face …

    iastate Repository record for Addressing stale gradients in asynchronous federated deep reinforcement learning (opens in a new tab)

  4. Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents

    … of state-of-the art offline and model-based reinforcement learning (RL) algorithms deteriorates significantly when subjected to severe data scarcity and the presence of heterogeneous agents. In this work, we propose a model-based offline RL method to approach this setting. Using all available …

    mit Repository record for Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents (opens in a new tab)

  5. An Introduction to Reinforcement Learning

    This thesis presents a new course textbook on reinforcement learning (RL) with a focus on algorithms and their properties. The textbook is suitable for a one-semester introductory undergraduate course on RL for students with prior experience in basic probability, linear algebra, and multivariable …

    harvard Repository record for An Introduction to Reinforcement Learning (opens in a new tab)

  6. The Limits of Temporal Abstractions for Reinforcement Learning with Sparse Rewards

    … abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, there has been little theoretical work aimed to characterize these properties precisely. This work …

    mit Repository record for The Limits of Temporal Abstractions for Reinforcement Learning with Sparse Rewards (opens in a new tab)

  7. Optimizing Priority-Based Search for Lifelong Multi-Agent Path Finding

    … scenarios. This work explores how learning-based methods can improve PBS decision-making. We develop supervised learning (SL) policies trained from high-quality beam search trajectories and reinforcement learning (RL) policies learned directly through simulation, enabling adaptive …

    mit Repository record for Optimizing Priority-Based Search for Lifelong Multi-Agent Path Finding (opens in a new tab)

  8. Learning from Experience: An Interactive and Ethical Curriculum for Teaching Reinforcement Learning

    … literacy are also increasingly important fields. Reinforcement learning (RL) plays and will continue to play an intense role in many systems, including online advertising, self-driving cars, and personalized tutoring. There is a corresponding need for education of RL. In my thesis work, I …

    mit Repository record for Learning from Experience: An Interactive and Ethical Curriculum for Teaching Reinforcement Learning (opens in a new tab)

  9. Inverse Reinforcement Learning and Routing Metric Discovery

    … thesis presents a method for utilizing inverse reinforcement learning (IRL)techniques for the purpose of discovering a composite metric used by a dynamic routing algorithm on an Internet Protocol (IP) network. The network and routing algorithm are modeled as a reinforcement learning (RL) agent …

    vt Repository record for Inverse Reinforcement Learning and Routing Metric Discovery (opens in a new tab)

  10. Improving traffic management efficiency through reinforcement learning-based traffic signal control and citywide transit simulation

    … framework that facilitates rapid prototyping of reinforcement learning (RL) and an automatic feature engineering method are proposed. Additionally, RL techniques are implemented to a digital twin of Chattanooga smart corridor. Regarding transit simulations, a toolkit for calibrating large-scale …

    utc Repository record for Improving traffic management efficiency through reinforcement learning-based traffic signal control and citywide transit simulation (opens in a new tab)

  11. Team Learning from Human Demonstration with Coordination Confidence

    … an array of techniques proposed to speed-up reinforcement learning (RL), learn- ing from human demonstration has a proven record of success. A related technique, called Human Agent Transfer (HAT), and its confidence-based derivatives have been successfully applied to single agent RL. This …

    usm Repository record for Team Learning from Human Demonstration with Coordination Confidence (opens in a new tab)

  12. Steps towards proof construction using reinforcement learning : environments and models for hypothesis-posing as subtask creation

    Despite recent advances in reinforcement learning (RL) that have allowed AI algorithms to master games such as Go from scratch, scant progress has been made on applying RL to one of the first tasks seen as susceptible to automation: theorem proving. I present steps towards training agents to …

    mit Repository record for Steps towards proof construction using reinforcement learning : environments and models for hypothesis-posing as subtask creation (opens in a new tab)

  13. Market making in dry waters : reinforcement learning strategies for market making in illiquid markets

    This thesis explores the application of reinforcement learning (RL) strategies to market making in illiquid markets. Traditional market making approaches often rely on static, rule-based strategies, which can struggle in illiquid environments. The study implements three RL algorithms: Deep …

    reykjavik Repository record for Market making in dry waters : reinforcement learning strategies for market making in illiquid markets (opens in a new tab)

  14. ARBITRAGE STRATEGIES IN PERPETUAL FUTURES AND STOCK INDEX FUTURES

    … arbitrage in perpetual futures, which track underlying prices through a funding swap mechanism. We show that the clamping function embedded in the mechanism—previously overlooked in the literature—creates inherent no-arbitrage bounds that persist even in the absence of transaction fees. Using two …

    nus Repository record for ARBITRAGE STRATEGIES IN PERPETUAL FUTURES AND STOCK INDEX FUTURES (opens in a new tab)

  15. Efficient Reinforcement Learning for Control

    … has evolved rapidly with the emergence of Reinforcement Learning (RL), offering promising solutions to a wide range of dynamic decision-making problems. However, the application of RL to real-world control systems is often hindered by computational inefficiencies, scalability issues, and a …

    vt Repository record for Efficient Reinforcement Learning for Control (opens in a new tab)

  16. Developing Intelligent Routing Algorithm over SDN: Reusable Reinforcement Learning Approach

    … that can fulfill various QoS requirements. Reinforcement Learning (RL) based routing algorithms have shown better performance than traditional approaches. We developed a QoS-aware, reusable RL routing algorithm, RLSR-Routing over SDN. During the learning process, our algorithm ensures …

    uwo Repository record for Developing Intelligent Routing Algorithm over SDN: Reusable Reinforcement Learning Approach (opens in a new tab)

  17. An application of stochastic dynamic programming to group revenue management

    … tool used in large industries, especially by airline companies. This tool aims at optimising revenues by a better control of inventory and pricing among other factors. In this thesis, a stochastic optimality control problem which consists of finding an optimal policy to when it is profitable (or …

    malta Repository record for An application of stochastic dynamic programming to group revenue management (opens in a new tab)

  18. AstroBug: automatic game bug detection using deep learning

    … further enhanced the framework by implementing Reinforcement Learning (RL) agent to autonomously gather datasets, effectively addressing the need for human players to collect data and manually browse through games. The enhancement was performed on a Role-Playing Game (RPG). The outcomes obtained …

    uoit Repository record for AstroBug: automatic game bug detection using deep learning (opens in a new tab)

  19. Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance

    Recent works have shown that tackling offline Reinforcement Learning (RL) with a conditional policy produces promising results. Decision Transformer (DT) have shown promising results in offline RL by leveraging sequence modeling. However, standard DTs rely on Returns-to-Go (RTG) tokens, which are …

    uoit Repository record for Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance (opens in a new tab)

  20. TCP congestion control using reinforcement learning

    … of Internet connectivity, with 85% of the worlds Internet traffic being TCP based. TCP however, is slow to adapt to changes in the network, drastically reducing the throughput at the first sign of possible congestion, thereby preventing rapid restoration of the throughput. Mitigating this …

    uoit Repository record for TCP congestion control using reinforcement learning (opens in a new tab)

Page 1 of 11