Description
This work explores combining state-of-the-art \gls{mbrl} algorithms focused on learning complex policies with large state-spaces and augmenting them with distributional reward perspective on \gls{rl} algorithms. Distributional \gls{rl} provides a probabilistic reward formulation as opposed to the classic \gls{rl} formulation which

This work explores combining state-of-the-art \gls{mbrl} algorithms focused on learning complex policies with large state-spaces and augmenting them with distributional reward perspective on \gls{rl} algorithms. Distributional \gls{rl} provides a probabilistic reward formulation as opposed to the classic \gls{rl} formulation which models the estimation of this distributional return. These probabilistic reward formulations help the agent choose highly risk-averse actions, which in turn makes the learning more stable. To evaluate this idea, I experiment in simulation on complex high-dimensional environments when subject under different noisy conditions.
Reuse Permissions
  • Downloads
    PDF (1.7 MB)
    Download count: 2

    Details

    Title
    • Learning Policies for Model-Based Reinforcement Learning Using Distributed Reward Formulation
    Contributors
    Date Created
    2021
    Resource Type
  • Text
  • Collections this item is in
    Note
    • Partial requirement for: M.S., Arizona State University, 2021
    • Field of study: Computer Science

    Machine-readable links