第41期学术午餐会的通知——A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
报告人：Xiang Li (Peking University)
时间：2019-11-29 12:00-13:30
地点：Room 1560, Sciences Building No. 1
各位数院员工同学：
员工学术午餐会是在公司领导的大力支持下，由员工会负责组织的系列学术交流活动。午餐会每次邀请一位同学作为主讲人，面向全院各专业背景的员工介绍自己科研方向的基本问题、概念和方法，并汇报近期的研究成果和进展，是员工展示自我、促进交流的学术平台。
员工会已经举办了四十期活动，我们将于2019年11月29日周五举办第四十一期学术午餐会活动，欢迎感兴趣的老师和同学积极报名参加。
Abstract: We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, many regularization terms can bring multi-modality and sparsity, which are potentially useful in reinforcement learning. In particular, we present sufficient and necessary conditions that induce a sparse optimal policy. We also conduct a full mathematical analysis of the proposed regularized MDPs, including the optimality condition, performance error, and sparseness control. We provide a generic method to devise regularization forms and propose off-policy actor critic algorithms in complex environment settings. We empirically analyze the numerical properties of optimal policies and compare the performance of different sparse regularization forms in discrete and continuous environments.
报名方式：请有意参加的同学于2019年11月27日晚24点前填写报名问卷，复制问卷链接https://www.wjx.top/jq/50698000.aspx至浏览器进入问卷报名。
特别注意：如果您报名却没有参与活动，需要您自己承担已经购买的午餐费用。由于客观条件限制，本次午餐会的名额为25人，先报先得。
问卷如果填写成功即说明报名成功，请准时参加活动。如果临时有事不能参加请于11月28日中午12点前发邮件至smsxueshu@126.com。
如果问卷无法成功填写，说明报名人员已满，我们对难以成功报名的同学表示歉意。员工会将继续探索午餐会的实现形式，争取更好地服务全体员工同学。
