English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Bayesian optimization is an efficient nonlinear optimization method where thequeries are carefully selected to gather information about the optimumlocation. Thus, in the context of policy search, it has been called activepolicy search. The main ingredients of Bayesian optimization for sampleefficiency are the probabilistic surrogate model and the optimal decisionheuristics. In this work, we exploit those to provide robustness to differentissues for policy search algorithms. We combine several methods and show howtheir interaction works better than the sum of the parts. First, to deal withinput noise and provide a safe and repeatable policy we use an improved versionof unscented Bayesian optimization. Then, to deal with mismodeling errors andimprove exploration we use stochastic meta-policies for query selection and anadaptive kernel. We compare the proposed algorithm with previous results inseveral optimization benchmarks and robot tasks, such as pushing objects with arobot arm, or path finding with a rover.

Robust Policy Search for Robot Navigation with Stochastic Meta-Policies