Variable Metric Reinforcement Learning Methods Applied to the Noisy Mountain Car Problem

Two variable metric reinforcement learning methods, the natural actor-critic algorithm and the covariance matrix adaptation evolution strategy, are compared on a conceptual level and analysed experimentally on the mountain car benchmark task with and without noise.

• Type: Conference
• Year: 2008
• Where: EWRL
• Authors: Verena Heidrich-Meisner, Christian Igel
• Keywords: Car Benchmark Task, Covariance Matrix Adaptation, EWRL 2008, Machine Learning, Variable Metric Reinforcement