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 8 of 8 for “"Multi-task reinforcement learning"”.

  1. Massively parallelized multi-task reinforcement learning

    Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy. However, online MTRL has largely been limited to training policies using …

    texas Repository record for Massively parallelized multi-task reinforcement learning (opens in a new tab)

  2. Task Generalized MDPs for Multi-Task Reinforcement Learning

    Reinforcement learning (RL) has seen widespread success in creating intelligent agents in several challenging domains. Yet, training RL agents remains prohibitively expensive in terms of the number of environment interactions required. One of the reasons for this inefficiency is that every new task …

    gatech Repository record for Task Generalized MDPs for Multi-Task Reinforcement Learning (opens in a new tab)

  3. Multi-Task Reinforcement Learning: From Single-Agent to Multi-Agent Systems

    … of the technology. The ability to develop these multi-task, multi-agent drone systems is limited by the lack of available training environments, as well as deficiencies of multi-task learning due to a phenomenon known as catastrophic forgetting. In this thesis, we present a set of simulation …

    vt Repository record for Multi-Task Reinforcement Learning: From Single-Agent to Multi-Agent Systems (opens in a new tab)

  4. Sample Complexity of Incremental Policy Gradient Methods for Solving Multi-Task Reinforcement Learning

    We consider a multi-task learning problem, where an agent is presented a number of N reinforcement learning tasks. To solve this problem, we are interested in studying the gradient approach, which iteratively updates an estimate of the optimal policy using the gradients of the value functions. The …

    vt Repository record for Sample Complexity of Incremental Policy Gradient Methods for Solving Multi-Task Reinforcement Learning (opens in a new tab)

  5. Adaptive algorithms for online learning in non-stationary environments

    Traditional online learning literature often assumes static environments, where fundamental properties like data distribution or action spaces do not change over time, and the learner competes against a single best action. This framework, however, fails to capture the complexity of many practical …

    uvic Repository record for Adaptive algorithms for online learning in non-stationary environments (opens in a new tab)

  6. A minimalist approach to deep multi-task learning

    <p>Multi-task learning is critical for real-life applications of machine learning. Modern approaches are characterised by algorithmic complexity, often unjustified, leading to impractical solutions. In contrast, this thesis demonstrates that a minimalistic alternative is possible, showing the …

    oxford Repository record for A minimalist approach to deep multi-task learning (opens in a new tab)

  7. Design and automation techniques for hIgh-performance mixed-signal circuits

    … variation-aware analog circuit optimization via multi-task reinforcement learning (RL) and task-space pruning. RobustAnalog is mainly designed to tackle the process-voltage-temperature (PVT) robustness in the analog design. Correlations between similar variations are modeled and conflicts between …

    texas Repository record for Design and automation techniques for hIgh-performance mixed-signal circuits (opens in a new tab)

  8. Adaptable and Scalable Multi-Agent Graph-Attention Communication

    … the cost of communication overhead. Within multi-agent reinforcement learning, synthesizing effective policies requires reasoning about when to communicate, whom to communicate with, and how to process messages. Meanwhile, in real-world problems, training policies and communication …

    gatech Repository record for Adaptable and Scalable Multi-Agent Graph-Attention Communication (opens in a new tab)