{"id":26765,"date":"2021-06-04T22:12:42","date_gmt":"2021-06-04T14:12:42","guid":{"rendered":"https:\/\/swarma.org\/?p=26765"},"modified":"2021-06-04T22:12:42","modified_gmt":"2021-06-04T14:12:42","slug":"%e5%91%a8%e6%97%a5%e7%9b%b4%e6%92%ad%e4%b8%a8%e5%9b%a0%e6%9e%9c%e5%90%af%e5%8f%91%e4%b8%8b%e7%9a%84%e4%b8%96%e7%95%8c%e5%bb%ba%e6%a8%a1%e4%b8%8e%e5%bc%ba%e5%8c%96%e5%ad%a6%e4%b9%a0%e5%86%b3%e7%ad%96","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=26765","title":{"rendered":"\u5468\u65e5\u76f4\u64ad\u4e28\u56e0\u679c\u542f\u53d1\u4e0b\u7684\u4e16\u754c\u5efa\u6a21\u4e0e\u5f3a\u5316\u5b66\u4e60\u51b3\u7b56\u65b9\u6cd5"},"content":{"rendered":"
\n
\n
\n

<\/p>\n

\n
\n
\n
\n
\n
\n

<\/section>\n<\/section>\n
\n
\n

\u5bfc\u8bed<\/strong><\/p>\n<\/section>\n<\/section>\n

\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n

\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u5728\u8fdb\u884c\u9884\u6d4b\u4efb\u52a1\u65f6\u5927\u591a\u6570\u60c5\u51b5\u4e0b\u4f1a\u5bfb\u627e\u8f93\u5165\u6570\u636e\u4e2d\u548c\u9884\u6d4b\u4efb\u52a1\u76f8\u5173\u7684\u4fe1\u606f\u3002\u4f46\u662f\u4e3a\u4e86\u8fbe\u5230\u66f4\u52a0\u9c81\u68d2\uff0c\u53ef\u91cd\u7528\u6027\u5f3a\u7684\u9884\u6d4b\u6548\u679c\uff0c\u9700\u8981\u8003\u8651\u66f4\u591a\u7684\u662f\u89c2\u5bdf\u6570\u636e\u5f53\u4e2d\u5b58\u5728\u6216\u9690\u542b\u7684\u56e0\u679c\u4fe1\u606f\uff0c\u800c\u975e\u5047\u76f8\u5173\u5173\u7cfb\u3002 \u5728\u5f3a\u5316\u5b66\u4e60\u4efb\u52a1\u5f53\u4e2d\uff0c\u5408\u9002\u7684\u56e0\u679c\u8868\u5f81\u3001\u56e0\u679c\u5efa\u6a21\u80fd\u591f\u5408\u7406\u5730\u63d0\u5347\u5f3a\u5316\u5b66\u4e60\u7684\u6027\u80fd\uff0c\u964d\u4f4e\u5176\u91c7\u6837\u590d\u6742\u5ea6\u3002\u4ece\u8be5\u52a8\u673a\u51fa\u53d1\uff0c\u6211\u4eec\u5c06\u5728\u56e0\u679c\u6a21\u578b\u8f85\u52a9\u73af\u5883\u8ba4\u77e5\uff0c\u53cd\u4e8b\u5b9e\u63a8\u7406\u4ee5\u53ca\u4e0b\u6e38\u51b3\u7b56\u4efb\u52a1\u4e24\u4e2a\u65b9\u9762\u8fdb\u884c\u4ecb\u7ecd\uff0c\u5176\u4e2d\u5305\u62ec\u90e8\u5206\u7ecf\u5178\u65b9\u6cd5\uff0c\u4ee5\u53ca\u8fd1\u671f\u5728\u56e0\u679c\u542f\u53d1\u4e0b\u7684\u51b3\u7b56\u65b9\u6cd5\u3002<\/span><\/strong><\/p>\n

<\/strong><\/p>\n

\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u667a\u6e90\u793e\u533a\uff0c\u7ec4\u7ec7\u56e0\u679c\u79d1\u5b66\u7cfb\u5217\u8bfb\u4e66\u4f1a\u7b2c\u4e8c\u5b63<\/a>\uff0c\u4ece\u57fa\u7840\u548c\u5b9e\u64cd\u89d2\u5ea6\u51fa\u53d1\uff0c\u7cbe\u8bfb\u4e24\u672c\u56e0\u679c\u79d1\u5b66\u65b9\u5411\u7684\u5165\u95e8\u6559\u6750\u3002\u8be6\u60c5\u89c1\u6587\u672b\u3002<\/strong><\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n

\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/section>\n<\/section>\n


<\/p>\n

\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5185\u5bb9\u7b80\u4ecb<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n

<\/section>\n

<\/h2>\n
\u672c\u671f\u5206\u4eab\u5c06\u4ecb\u7ecd\u56e0\u679c\u542f\u53d1\u51b3\u7b56\u63a8\u7406\u4efb\u52a1\u7684\u95ee\u9898\u4ee5\u53ca\u6574\u4f53\u6d41\u7a0b\uff0c\u5305\u62ec\u56e0\u679c\u6a21\u578b\u8f85\u52a9\u73af\u5883\u8ba4\u77e5\uff0c\u53cd\u4e8b\u5b9e\u63a8\u7406\u4ee5\u53ca\u4e0b\u6e38\u51b3\u7b56\u4efb\u52a1\u3002\u5728\u73af\u5883\u8ba4\u77e5\u90e8\u5206\u5c06\u7b80\u5355\u7684\u4ecb\u7ecd\u56e0\u679c\u53d1\u73b0\uff0c\u56e0\u679c\u6a21\u578b\u5efa\u6a21\uff0c\u56e0\u679c\u8868\u793a\u5b66\u4e60\u7684\u5e38\u89c1\u65b9\u6cd5\uff0c\u4ee5\u53ca\u8fd1\u671f\u5728\u56e0\u679c\u89e3\u8026\u8868\u5f81\u5b66\u4e60\u4e0a\u7684\u63a2\u7d22\u3002\u4e0b\u6e38\u51b3\u7b56\u4efb\u52a1\u4e0a\uff0c\u5c06\u4ecb\u7ecd\u5f3a\u5316\u5b66\u4e60\u7684\u57fa\u672c\u77e5\u8bc6\uff0cModel-based RL\u4e2d\u7684World Models\u65b9\u6cd5\uff0c\u4ee5\u53ca\u8fd1\u671f\u7684\u56e0\u679c\u6a21\u578b\u8f85\u52a9\u5f3a\u5316\u5b66\u4e60\u7684\u57fa\u4e8e\u56e0\u679c\u4e16\u754c\u6a21\u578b\u7684\u5f3a\u5316\u5b66\u4e60\u65b9\u6cd5\u3002<\/span><\/section>\n


<\/p>\n


<\/p>\n

\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u4e3b\u8bb2\u4ecb\u7ecd<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n


<\/p>\n

<\/p>\n

\u6768\u68a6\u6708<\/strong>\uff0c\u4f26\u6566\u5927\u5b66\u5b66\u9662\u8ba1\u7b97\u673a\u4e13\u4e1a\u535a\u58eb\u4e00\u5e74\u7ea7\uff0c\u5bfc\u5e08\u4e3a\u6c6a\u519b\u6559\u6388\uff0c\u66fe\u5728WWW\/CVPR\u4e0a\u53d1\u8868\u8fc7\u4e00\u4f5c\u8bba\u6587\u3002\u76ee\u524d\u5728\u534e\u4e3a\u8bfa\u4e9a\u65b9\u821f\u51b3\u7b56\u63a8\u7406\u5b9e\u9a8c\u5ba4\u56e0\u679c\u7ec4\u5b9e\u4e60\uff0c\u7814\u7a76\u5174\u8da3\u5305\u62ec\u56e0\u679c\u8868\u793a\u5b66\u4e60\uff0c\u56e0\u679c\u5f3a\u5316\u5b66\u4e60\u3002<\/span><\/p>\n


<\/p>\n

\u53c2\u8003\u6587\u732e<\/span><\/strong><\/span><\/h2>\n
\u2022 Xun Zheng, Bryon Aragam, Pradeep K Ravikumar, and Eric PXing. Dags with no tears: Continuous optimization for struc-ture learning. InAdvances in Neural Information ProcessingSystems, pages 9472\u20139483, 20<\/span><\/section>\n
\u2022 Mooij, J. M., Peters, J., Janzing, D., Zscheischler, J., andSch \u0308olkopf, B.Distinguishing cause from effect using observational data: Methods and benchmarks.J.Mach. Learn. Res., 17:32:1\u201332:102, 2016<\/span><\/section>\n
\u2022 Yue Yu, Jie Chen, Tian Gao, and Mo Yu.  Dag-gnn: Dagstructure learning with graph neural networks.arXiv preprintarXiv:1904.10098, 2019<\/span><\/section>\n
\u2022 Francesco Locatello, Stefan Bauer, Mario Lucic, GunnarR \u0308atsch, Sylvain Gelly, Bernhard Sch \u0308olkopf, and OlivierBachem. Challenging common assumptions in the unsuper-vised learning of disentangled representations.arXiv preprintarXiv:1811.12359, 2018.<\/span><\/section>\n
\u2022 Yang M , Liu F , Chen Z , et al. CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models[J]. 2020.<\/span><\/section>\n
\u2022 X Shen,F Liu,H Dong,Q Lian,T Zhang. Disentangled Generative Causal Representation Learning<\/span><\/section>\n
\u2022 David Ha, J\u00fcrgen Schmidhuber:World Models. CoRR abs\/1803.10122 (2018)<\/span><\/section>\n
\u2022 Minne Li, Mengyue Yang, Furui Liu, Xu Chen, Zhitang Chen, Jun Wang: Causal World Models by Unsupervised Deconfounding of Physical Dynamics. CoRR abs\/2012.14228 (2020)<\/span><\/section>\n
\u2022 Schlkopf B , Locatello F , Bauer S , et al. Towards Causal Representation Learning[J]. 2021.<\/span><\/section>\n
\u2022 Judea Pearl.Causality. Cambridge university press, 20<\/span><\/section>\n
\u2022 Peters J , Janzing D , B Sch\u00f6lkopf. Elements of Causal Inference – Foundations and Learning Algorithms. 2017.<\/span><\/section>\n


<\/h4>\n

\u53c2\u4e0e\u65f6\u95f4\uff1a<\/span><\/strong><\/span><\/h4>\n

\u65f6\u95f4\uff1a6\u67086\u65e5\uff08\u5468\u65e5\uff09\u4e0a\u534810:00-12:00<\/span><\/p>\n


<\/p>\n

\u76f4\u64ad\u65b9\u5f0f\uff1a\u817e\u8baf\u4f1a\u8bae\u76f4\u64ad<\/span><\/strong><\/span><\/section>\n

<\/span><\/strong><\/span><\/section>\n