A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2202.11797v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
[article]
<span title="2022-02-25">2022</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2022-02-23">2022</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.11797v1">arXiv:2202.11797v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vgpkrtg3ffbjtdbp6lsmxnyvna">fatcat:vgpkrtg3ffbjtdbp6lsmxnyvna</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.11797v1">arXiv:2202.11797v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vgpkrtg3ffbjtdbp6lsmxnyvna">fatcat:vgpkrtg3ffbjtdbp6lsmxnyvna</a> </span>
One of the goals of Explainable AI (XAI) is to determine which input components were relevant for a classifier decision. This is commonly know as saliency attribution. Characteristic functions (from cooperative game theory) are able to evaluate partial inputs and form the basis for theoretically "fair" attribution methods like Shapley values. Given only a standard classifier function, it is unclear how partial input should be realised. Instead, most XAI-methods for black-box classifiers like
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.11797v2">arXiv:2202.11797v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gv6z7ffscrdyhaqjz2cyvy5fli">fatcat:gv6z7ffscrdyhaqjz2cyvy5fli</a>
</span>
more »
... ral networks consider counterfactual inputs that generally lie off-manifold. This makes them hard to evaluate and easy to manipulate. We propose a setup to directly train characteristic functions in the form of neural networks to play simple two-player games. We apply this to the game of Connect Four by randomly hiding colour information from our agents during training. This has three advantages for comparing XAI-methods: It alleviates the ambiguity about how to realise partial input, makes off-manifold evaluation unnecessary and allows us to compare the methods by letting them play against each other.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220519235038/https://arxiv.org/pdf/2202.11797v2.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/6a/ef/6aef611ce097c12d7f194bbbfa21af7c018f8c8e.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.11797v2" 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>