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 “"Meta-RL"”.

  1. Efficient Meta-Reinforcement Learning

    In Meta-Reinforcement Learning (meta-RL) agents are trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The standard practice to build training sets in meta-RL is to use dense coverage of task distributions, generating a very large set of training tasks. …

    whiterose Download PDF for Efficient Meta-Reinforcement Learning (opens in a new tab)

  2. Fast adaptation via meta reinforcement learning

    <p>Reinforcement Learning (RL) is a way to train artificial agents to autonomously interact with the world. In practice however, RL still has limitations that prohibit the deployment of RL agents in many real world settings. This is because RL takes long, typically requires human oversight, and …

    oxford Repository record for Fast adaptation via meta reinforcement learning (opens in a new tab)

  3. Representations in zero-shot meta-reinforcement learning

    … a sequence of decisions to interact with the world. When interacting with its environment, an agent will encounter new situations that it has not previously encountered and for which we cannot provide an explicit representation of the environment. In this case, the agent must learn about its …

    oxford Repository record for Representations in zero-shot meta-reinforcement learning (opens in a new tab)

  4. Advances in meta-reinforcement learning and imitation learning

    … critical aspects of learning for interactive AI: meta-reinforcement learning (meta-RL) and imitation learning (IL). <br><br>In the first part, we address the problem of improving the sample efficiency of reinforcement learning (RL) algorithms through meta-learning. By developing novel meta-RL …

    oxford Repository record for Advances in meta-reinforcement learning and imitation learning (opens in a new tab)

  5. Meta multi-objective reinforcement learning for communication load balancing

    … the traffic load by offloading users from overloaded cells to less crowded neighboring ones. In this thesis, we study multi-objective reinforcement learning (MORL) and meta reinforcement learning (meta-RL) for load balancing to learn highly customized policies for different trade-offs between …

    manitoba Repository record for Meta multi-objective reinforcement learning for communication load balancing (opens in a new tab)

  6. Meta-reinforcement learning approaches to process control

    Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. Many industrial processes have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller …

    ubc Repository record for Meta-reinforcement learning approaches to process control (opens in a new tab) Download PDF for Meta-reinforcement learning approaches to process control (opens in a new tab)

  7. Deep reinforcement learning methods

    … focuses on Deep Reinforcement Learning (Deep RL) methods and their applications in games. It provides an in-depth analysis of existing state-of-the-art Deep RL methods and introduces novel techniques based on the concept of meta-RL for achieving high performance with improved …

    greece Repository record for Deep reinforcement learning methods (opens in a new tab)

  8. Scaling Online Reinforcement Learning In Embodied AI To 64K Steps

    … approach for in-context reinforcement learning (RL) for embodied agents. With ReLIC, agents are capable of adapting to new environments using 64,000 steps of in-context experience with full attention mechanism while being trained through self-generated experience via RL. We achieve this by …

    gatech Repository record for Scaling Online Reinforcement Learning In Embodied AI To 64K Steps (opens in a new tab)

  9. Deep reinforcement learning agents for industrial control system design

    Deep reinforcement learning (RL) is an optimization-driven framework for producing control strategies without explicit reliance on process models. Powerful new methods in RL are often showcased for their performance on difficult simulated tasks In contrast, industrial control system design has many …

    ubc Repository record for Deep reinforcement learning agents for industrial control system design (opens in a new tab) Download PDF for Deep reinforcement learning agents for industrial control system design (opens in a new tab)

  10. Towards data-efficient deployment of reinforcement learning systems

    … Traditional reinforcement learning (RL) struggles with this requirement in two ways. Firstly, iterative exploration of unconstrained environment dynamics yields numerous uninformative updates and consequently slow adaptation. Secondly, final policies have no capacity to adapt to …

    oxford Repository record for Towards data-efficient deployment of reinforcement learning systems (opens in a new tab)

  11. On Safety in Sequential Decision Learning

    … Reinforcement Learning from Human Feedback (RA-RLHF), which incorporates Conditional Value at Risk principles during model fine-tuning. This approach effectively reduces toxic content generation while maintaining model performance on general tasks, contributing to safer AI deployment. Addressing …

    tamu Repository record for On Safety in Sequential Decision Learning (opens in a new tab)

  12. Capability-Aware Shared Hypernetworks for Heterogeneous Multi-Agent Coordination

    … inspired by recent work in transfer learning and meta-RL, we propose Capability-Aware Shared Hypernetworks (CASH), a new soft weight sharing architecture for heterogeneous coordination that use hypernetworks to explicitly reason about continuous agent capabilities in addition to local …

    gatech Repository record for Capability-Aware Shared Hypernetworks for Heterogeneous Multi-Agent Coordination (opens in a new tab)

  13. Practical reinforcement learning for adaptive robotic manipulation: Sample efficiency, sim-to-real transfer, and context inference

    … in the field of reinforcement learning (RL) for robot manipulation. The central challenges compromising the practical use of RL are addressed, including data efficiency, sim-to-real transfer, and context-aware generalization to unseen tasks. The first contribution addresses the …

    uvic Repository record for Practical reinforcement learning for adaptive robotic manipulation: Sample efficiency, sim-to-real transfer, and context inference (opens in a new tab)

  14. Efficient automated deep learning via task-conditioned meta-learning and hyperparameter optimization

    … solved problems. These challenges are particularly acute in deep reinforcement learning, where training is costly, unstable, and extraordinarily sensitive to algorithmic configuration. This thesis addresses the question: how can we make deep learning, and deep reinforcement learning in …

    freiburg-diss Repository record for Efficient automated deep learning via task-conditioned meta-learning and hyperparameter optimization (opens in a new tab)

  15. Artificial Intelligence-Driven Rate Adaptive and Perceptual-Aware Rich Media Delivery in 5G and Beyond Networks

    … Multi-Agent Deep Reinforcement Learning (MADRL) framework for region-aware ABR control in tile-based 360-degree video streaming. EDGE360 employs the Counterfactual Multi-Agent (COMA) policy gradient method to optimize bitrate allocation across viewport, marginal, and background regions, using …

    dcu Download PDF for Artificial Intelligence-Driven Rate Adaptive and Perceptual-Aware Rich Media Delivery in 5G and Beyond Networks (opens in a new tab)

  16. Advancing Machine Learning for Resilient and Safe Critical Systems: From Theory to Applications

    … For operational resilience we introduces a meta-guided gradient-free reinforcement learning framework for critical load restoration in power distribution systems, enabling rapid adaptation to unseen outage scenarios under renewable uncertainty while improving restoration speed and …

    vt Repository record for Advancing Machine Learning for Resilient and Safe Critical Systems: From Theory to Applications (opens in a new tab)

  17. Towards automating reinforcement learning

    … in recent years. Reinforcement learning (RL), the branch of machine learning concerned with learning general agents through reward signals and trial-and-error in the agent's environment has also had breakthrough successes in fields as diverse as video game playing, board games, helicopter …

    freiburg-diss Repository record for Towards automating reinforcement learning (opens in a new tab)