查看“Seminar”的源代码


为了加强IIP组的学术交流与科研需要，举办2018学术讨论班，每周五下午2点，报告内容见下表，欢迎参加交流。

<span style="font-size:small;">指导老师：[http://cs.nju.edu.cn/zhangl/ 张雷]</span>

<span style="font-size:small;">组内成员：程浩，张怡，朱恺，冯伟赞</span>

&nbsp;

{| align="left" border="1" cellpadding="1" cellspacing="1" style="width: 812px;"
|-
! colspan="1" scope="col" style="width: 95px;" | 时间地点
! scope="col" style="width: 144px;" | 报告人
! scope="col" style="width: 370px;" | 报告题目
! scope="col" style="width: 182px;" | 资料链接
|-
| colspan="1" rowspan="2" style="width: 95px; text-align: center;" | 
3.23下午3点

224教室

| style="width: 144px; border-color: rgb(0, 0, 0);" | <p style="text-align: center;">张怡</p> 
| style="width: 370px; border-color: rgb(0, 0, 0); text-align: center;" | Instance Specific Discriminative Modal Pursuit：<br/> A Serialized Approach*
| style="width: 182px; text-align: center;" | [http://proceedings.mlr.press/v77/yang17a.html 文献]
|-
| style="width: 144px;" | <p style="text-align: center;">冯伟赞</p> 
| style="width: 370px; text-align: center;" | Text Matching as Image Recognition
| style="width: 182px; text-align: center;" | [https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11895 文献]
|-
| colspan="1" rowspan="2" style="width: 95px; text-align: center;" | 
4.8下午2点

223教室

| style="width: 144px; text-align: center;" | &nbsp;程浩&nbsp;
| style="width: 370px; text-align: center;" | Probably Approximately Efficient<br/> Combinatorial Auctions via Machine Learning
| style="width: 182px; text-align: center;" | [https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/15040 文献]
|-
| style="width: 144px; text-align: center;" | 朱恺
| style="width: 370px; text-align: center;" | Deterministic Policy Gradient Algorithms
| style="width: 182px; text-align: center;" | [http://proceedings.mlr.press/v32/silver14.html 文献]
|-
| colspan="1" style="width: 95px; text-align: center;" | 
4.13号下午2点

223教室

| style="width: 144px; text-align: center;" | 张雷
| style="width: 370px; text-align: center;" | Optimal auctions through deep learning.
| style="width: 182px; text-align: center;" | [https://arxiv.org/abs/1706.03459 文献]
|-
| colspan="1" rowspan="2" style="width: 95px; text-align: center;" | 
4.20下午2点

319教室

| style="width: 144px; text-align: center;" | 张怡
| style="width: 370px; text-align: center;" | Instance Specific Discriminative Modal Pursuit：<br/> A Serialized Approach*代码分析
| style="width: 182px; text-align: center;" | [http://proceedings.mlr.press/v77/yang17a.html 文献]
|-
| style="width: 144px; text-align: center;" | 程浩
| style="width: 370px; text-align: center;" | Safe and Nested Subgame Solving for<br/> Imperfect-Information Games
| style="width: 182px; text-align: center;" | [http://papers.nips.cc/paper/6671-safe-and-nested-subgame-solving-for-imperfect-information-games 文献]
|-
| colspan="1" rowspan="2" style="width: 95px; text-align: center;" | 
4.27下午2点

224教室

| style="width: 144px; text-align: center;" | 张雷
| style="width: 370px; text-align: center;" | Mechanism Design in Social Networks
| style="width: 182px; text-align: center;" | [http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14879/13816 文献]
|-
| style="width: 144px; text-align: center;" | 朱恺
| style="width: 370px; text-align: center;" | 
= <span style="font-size:small;"><span style="line-height:1.3"><span style="background-color:#ffffff"><span style="outline:0px !important"><font color="#333333"><font face="sans-serif">A new approach on multi-agent Multi-Objective Reinforcement Learning based on agents' preferences</font></font></span></span></span></span> =

| style="width: 182px; text-align: center;" | [https://ieeexplore.ieee.org/abstract/document/8324111/ <font size="2">文献</font>]
|}

&nbsp;