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 6 of 6 for “"Modular reinforcement learning"”.

  1. Action selection in modular reinforcement learning

    Modular reinforcement learning is an approach to resolve the curse of dimensionality problem in traditional reinforcement learning. We design and implement a modular reinforcement learning algorithm, which is based on three major components: Markov decision process decomposition, module training, …

    texas Repository record for Action selection in modular reinforcement learning (opens in a new tab)

  2. Integrating reinforcement learning into a programming language

    Reinforcement learning is a promising solution to the intelligent agent problem, namely, given the state of the world, which action should an agent take to maximize goal attainment. However, reinforcement learning algorithms are slow to converge for larger state spaces and using reinforcement …

    gatech Repository record for Integrating reinforcement learning into a programming language (opens in a new tab)

  3. A modular attention hypothesis for modeling visuomotor behaviors

    … this work, we seek to understand and model this modular attention mechanism for humans in a range of behavioral settings. We explain this approach to understanding modular attention at three levels based on David Marr’s paradigm: the computation theory level, the representation and algorithm …

    texas Repository record for A modular attention hypothesis for modeling visuomotor behaviors (opens in a new tab)

  4. Ρομποτική λαβή και χειρισμός αντικειμένων με επαφή με το περιβάλλον

    … space around the target object. Both methods use reinforcement learning to train policies that use two pushing primitives, in order to totally singulate the target in the minimum number of actions. The first proposed method is called SplitDQN and modifies Deep Q-Network (DQN) by splitting the …

    greece Repository record for Ρομποτική λαβή και χειρισμός αντικειμένων με επαφή με το περιβάλλον (opens in a new tab)

  5. Robotic grasping and manipulation of unknown objects in clutter

    … a prehensile grasp. The proposed methods employ reinforcement learning to train policies that use two pushing primitives for object singulation with the minimum number of actions. In particular, we use the Deep Q-Network (DQN) algorithm and demonstrate that we can learn optimal push policies …

    greece Repository record for Robotic grasping and manipulation of unknown objects in clutter (opens in a new tab)