A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2010.05380v4.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Efficient Wasserstein Natural Gradients for Reinforcement Learning
[article]
<span title="2021-03-18">2021</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2021-03-17">2021</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v3">arXiv:2010.05380v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ttahc527mzfbxaepptqvsgonze">fatcat:ttahc527mzfbxaepptqvsgonze</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v3">arXiv:2010.05380v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ttahc527mzfbxaepptqvsgonze">fatcat:ttahc527mzfbxaepptqvsgonze</a> </span>
<span title="2020-10-12">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v1">arXiv:2010.05380v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cyewmu4x5rfpzhtcrlnenuew6a">fatcat:cyewmu4x5rfpzhtcrlnenuew6a</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v1">arXiv:2010.05380v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cyewmu4x5rfpzhtcrlnenuew6a">fatcat:cyewmu4x5rfpzhtcrlnenuew6a</a> </span>
<span title="2020-11-02">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v2">arXiv:2010.05380v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rolj5ewyyja5fiz6jmeulajxqy">fatcat:rolj5ewyyja5fiz6jmeulajxqy</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v2">arXiv:2010.05380v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rolj5ewyyja5fiz6jmeulajxqy">fatcat:rolj5ewyyja5fiz6jmeulajxqy</a> </span>
A novel optimization approach is proposed for application to policy gradient methods and evolution strategies for reinforcement learning (RL). The procedure uses a computationally efficient Wasserstein natural gradient (WNG) descent that takes advantage of the geometry induced by a Wasserstein penalty to speed optimization. This method follows the recent theme in RL of including a divergence penalty in the objective to establish a trust region. Experiments on challenging tasks demonstrate
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v4">arXiv:2010.05380v4</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7bhuob2ngjfdbfzmn4q44gyxra">fatcat:7bhuob2ngjfdbfzmn4q44gyxra</a>
</span>
more »
... ements in both computational cost and performance over advanced baselines.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210329045527/https://arxiv.org/pdf/2010.05380v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/75/6e/756e18d759584c120d17d843e1c0be5375d80316.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05380v4" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>