Real time targeted exploration in large domains

17 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation (2016, positive): “The TEXPLORE algorithm learns multiple decision tree models from subsets of experience to represent uncertainty in model predictions [9].”
RTMBA: A Real-Time Model-Based Reinforcement Learning Architecture for robot control (2011, methodology): “All of the algorithms used random forests to model the domain, similar to the approach taken by Hester and Stone [10].”
Learning and Using Models (2012, methodology): “TEXPLORE has been used in a gridworld with over 300,000 states (Hester and Stone, 2010) and run in real-time on an autonomous vehicle (Hester et al, 2011)(4).”
The Open-Source TEXPLORE Code Release for Reinforcement Learning on Robots (2013, background): “rl env: This package includes a variety of benchmark RL domains such as Fuel World [8], Taxi [4], Mountain Car [19], Cart-Pole [19], Light World [12], and the simulated car velocity control domain presented in Section 5.”