Skip to main content Skip to main navigation


Policy Search with High-Dimensional Context Variables

Voot Tangkaratt; Herke van Hoof; Simone Parisi; Gerhard Neumann; Jan Peters; Masashi Sugiyama
In: Satinder Singh; Shaul Markovitch (Hrsg.). Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence (AAAI-2017), February 4-9, San Francisco, California, USA, Pages 2632-2638, AAAI Press, 2017.


Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application of unsupervised dimensionality reduction methods to the context variables, such as principal component analysis, is insufficient as task-relevant input may be ignored. In this paper, we propose a contextual policy search method in the model-based relative entropy stochastic search framework with integrated dimensionality reduction. We learn a model of the reward that is locally quadratic in both the policy parameters and the context variables. Furthermore, we perform supervised linear dimensionality reduction on the context variables by nuclear norm regularization. The experimental results show that the proposed method outperforms naive dimensionality reduction via principal component analysis and a state-of-the-art contextual policy search method.

Weitere Links