Search
Skip to Search Results
Filter
Author / Creator / Contributor
Departments
Languages
Collections
Subject / Keyword
- 1Classification
- 1Classification Calibration
- 1Classification-Based Policy Iteration
- 1Excess risk
- 1Factored Linear Models
- 1Factored Semi-linear Models
Year
Item type
Supervisors
-
Spring 2012
We study linear estimation based on perturbed data when performance is measured by a matrix norm of the expected residual error, in particular, the case in which there are many unknowns, but the “best” estimator is sparse, or has small L1-norm. We propose a Lasso-like procedure that finds the...
-
Toward Practical Reinforcement Learning Algorithms: Classification Based Policy Iteration and Model-Based Learning
DownloadSpring 2017
In this dissertation, we advance the theoretical understanding of two families of Reinforcement Learning (RL) methods: Classification-based policy iteration (CBPI) and model-based reinforcement learning (MBRL) with factored semi-linear models. In contrast to generalized policy iteration, CBPI...
1 - 2 of 2