Feature Reinforcement Learning

    Project: Research

    Project Details

    Description

    This project aims to bridge the gap between theory and practice in reinforcement learning (RL). General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, RL is well-developed for small finite state Markov decision processes (MDPs). Up to now, extracting the right state representations out of bare observations, that is, reducing the general agent setup to the MDP framework, is an art that involves significant effort by designers. The primary goal of this project is to automate the reduction process and thereby significantly expand the scope of many existing RL algorithms and the agents that employ them.
    StatusFinished
    Effective start/end date1/07/1230/06/17

    Fingerprint

    Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.