Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2018 May 29;12:24. doi: 10.3389/fnbot.2018.00024

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2018 Ewerton, Rother, Weimar, Kollegger, Wiemeyer, Peters and Maeda.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Sampling with relevance weighting. (A) Samples from the original distribution. (B) Samples to optimize the distribution over trajectories with respect to beginning at the start position. (C) Samples to optimize the distribution over trajectories with respect to passing through the center of the window. (D) Samples to optimize the distribution over trajectories with respect to reaching the end position. The proposed algorithm explores for each objective a large range of values for the policy parameters that are relevant to that objective, while sampling values close to the mean for the other policy parameters. The variance of the irrelevant parameters is recovered according to Equation (43). Therefore, after optimizing for each objective, the distribution over the relevant parameters is updated, while the distribution over the irrelevant parameters is preserved.