2026-05-23T17:50:54Zhttps://keep.lib.asu.edu/oai/request

oai:keep.lib.asu.edu:node-1616942024-12-23T18:01:48Zoai_pmh:alloai_pmh:repo_items

161694 https://hdl.handle.net/2286/R.2.N.161694 http://rightsstatements.org/vocab/InC/1.0/ All Rights Reserved 2021 38 pages Masters Thesis Academic theses Text eng Agarwal, Nikhil Ben Amor, Heni Phielipp, Mariano DV, Hemanth Arizona State University Partial requirement for: M.S., Arizona State University, 2021 Field of study: Computer Science 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. Computer Science Deep learning distributed reinforcement learning Model Predictive Control model-based reinforcement learning Reinforcement Learning Learning Policies for Model-Based Reinforcement Learning Using Distributed Reward Formulation