Online Program Home
My Program

Abstract Details

Activity Number: 127 - SPEED: Statistical Learning and Data Science Speed Session 1, Part 1
Type: Contributed
Date/Time: Monday, July 29, 2019 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Learning and Data Science
Abstract #306429 Presentation 1 Presentation 2
Title: Efficient Randomized Algorithms for Continuous Space Reinforcement Learning
Author(s): Mohamad Kazem Shirani Faradonbeh* and Ambuj Tewari and George Michailidis
Companies: University of Florida and University of Michigan and University of Florida
Keywords: Randomized Policies; Exploration-Exploitation; Action Perturbation; Residual Bootstrap; Covariate Resampling; Posterior Sampling
Abstract:

Reinforcement learning problems concerning decision-making under uncertainty for continuous state and action spaces received a lot of attentions recently. The standard approach consists of balancing the exploration and the exploitation in models of linear dynamics and quadratic cost functions (LQ). The state-of-the-art results prescribe a class of randomized policies as practical methods with performance guarantees.

However, for the existing randomized algorithms, a comprehensive comparison is not currently available in the literature. This work compares various randomization procedures according to several important criteria such as learning accuracy, robustness to mis-specification, and regret due to uncertainty. We analyze different parametric and non-parametric schemes including action perturbation, posterior sampling, estimate randomization, residual bootstrap, and covariate resampling.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program