10:["$","div",null,{"className":"Post-module__aBOVGG__post","style":{"display":"flex","flexDirection":"column","alignItems":"center","gap":"8px","flex":"1","width":"100%","padding":"12px"},"children":[["$","div",null,{"className":"$undefined","style":{"display":"flex","gap":"0.4rem","flexWrap":"wrap","width":"100%"},"children":[false,[["$","a","323A",{"href":"/323A","className":"Post-module__aBOVGG__fg","style":{},"children":"読みたい"}],["$","a","25AB",{"href":"/25AB","className":"Post-module__aBOVGG__fg","style":{},"children":"Offline Reinforcement Learning"}],["$","a","B54F",{"href":"/B54F","className":"Post-module__aBOVGG__fg","style":{},"children":"Implicit Q-Learning"}]]]}],["$","article",null,{"className":"article","children":[["$","div",null,{"className":"$undefined","style":{"display":"flex","justifyContent":"space-between","flexWrap":"wrap","width":"100%"},"children":[["$","h2",null,{"style":{"margin":"0.2rem"},"children":["$","a",null,{"href":"/152F","children":"Offline Reinforcement Learning with Implicit Q-Learning"}]}],["$","div",null,{"className":"$undefined","style":{"display":"flex","justifyContent":"end","alignItems":"center","flex":"1","textAlign":"right","whiteSpace":"nowrap"},"children":["$","div",null,{"children":"2021/12/8 2:11:00"}]}]]}],["$","div",null,{"className":"article_body","dangerouslySetInnerHTML":{"__html":"

https://arxiv.org/abs/2110.06169\n

"}}]]}],["$","div",null,{"className":"$undefined","style":{"display":"flex","gap":"0.4rem","flexWrap":"wrap","width":"100%"},"children":[["$","a","",{"href":"/","className":"Post-module__aBOVGG__bg","style":{"opacity":0},"children":"あれ"}],[]]}]]}]