Details

Autor(en) / Beteiligte

• Bădică, Amelia
• Bădică, Costin
• Ivanović, Mirjana
• Logofătu, Doina

Titel

Experiments with Solving Mountain Car Problem Using State Discretization and Q-Learning

Ist Teil von

• Intelligent Information and Database Systems, p.142-155

Ort / Verlag

Cham: Springer International Publishing

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• The aim of this paper is to explore the model of the Mountain Car Problem. We provide insight into the physics behind the model. We present some experimental results obtained by numerically simulating the model. We also propose a reinforcement learning approach for deriving an optimal control policy combining model discretization and Q-learning.