A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1508.04186v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Distributed Deep Q-Learning
[article]
<span title="2015-10-15">2015</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2015-08-18">2015</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1508.04186v1">arXiv:1508.04186v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rystb6awwfcwvjnsbcmn62gqpq">fatcat:rystb6awwfcwvjnsbcmn62gqpq</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1508.04186v1">arXiv:1508.04186v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rystb6awwfcwvjnsbcmn62gqpq">fatcat:rystb6awwfcwvjnsbcmn62gqpq</a> </span>
We propose a distributed deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is based on the deep Q-network, a convolutional neural network trained with a variant of Q-learning. Its input is raw pixels and its output is a value function estimating future rewards from taking an action given a system state. To distribute the deep Q-network training, we adapt the DistBelief software framework to the context
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1508.04186v2">arXiv:1508.04186v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xpwce2w2xnafthaeffdyjktmeu">fatcat:xpwce2w2xnafthaeffdyjktmeu</a>
</span>
more »
... of efficiently training reinforcement learning agents. As a result, the method is completely asynchronous and scales well with the number of machines. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to achieve reasonable success on a simple game with minimal parameter tuning.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823104928/https://arxiv.org/pdf/1508.04186v2.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/fc/d1/fcd13107bdd1df39ad0587def6410e216a1cff33.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1508.04186v2" 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>