Search
Skip to Search Results
Filter
Subject / Keyword
- 1Approximate Value/Policy Iteration
- 1Error Propagation
- 1Machine Learning
- 1Model Selection
- 1Regularization
- 1Regularized Fitted Q-Iteration
Collections
Author / Creator / Contributor
Year
Languages
Item type
Departments
-
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 - 1 of 1