Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Sample-efficiency and reliability remain major bottlenecks toward wide adoption of
reinforcement learning algorithms in continuous settings with high-dimensional perceptual …
reinforcement learning algorithms in continuous settings with high-dimensional perceptual …
Deep Non-Parametric Abstractions of Markov Decision Processes for Exact Planning
AK Shrestha - 2024 - ir.library.oregonstate.edu
Abstract Markov Decision Processes (MDPs) provide a powerful framework for sequential
decision making, but solving large-scale MDPs that model real-world problems remains a …
decision making, but solving large-scale MDPs that model real-world problems remains a …