Search
Skip to Search Results
Filter
Subject / Keyword
- 2Machine Learning
- 1Approximate Value/Policy Iteration
- 1Costly Observations
- 1Error Propagation
- 1Model Selection
- 1Online Learning
Supervisors
Author / Creator / Contributor
Year
Collections
Languages
Item type
Departments
-
Spring 2013
This work introduces the “online probing” problem: In each round, the learner is able to purchase the values of a subset of features for the current instance. After the learner uses this information to produce a prediction for this instance, it then has the option of paying for seeing the full...
-
Fall 2011
This thesis studies the reinforcement learning and planning problems that are modeled by a discounted Markov Decision Process (MDP) with a large state space and finite action space. We follow the value-based approach in which a function approximator is used to estimate the optimal value function....
1 - 2 of 2