2024年图灵奖得主、强化学习之父Richard S. Sutton教授首次在中国开设完整的系统性强化学习课程！上海创智学院、上海交通大学人工智能学院与Openmind Research Institute将在2026年7月联合推出为期三周的暑期强化学习课程，特邀2024年图灵奖得主、“强化学习之父”Richard S. Sutton教授亲临沪上，领衔主讲。现面向全国及国际相关高校及科研院所公开遴选优秀学生与青年学者，相关事宜公告如下。
The first complete and systematic reinforcement learning course delivered in China by Prof. Richard S. Sutton! Jointly launched by Shanghai Innovation Institute (SII), School of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), and Openmind Research Institute (Openmind), the three-week 2026 Summer School is proud to present a series of masterclasses in Reinforcement Learning (RL) in July 2026, We are exceptionally honored to invite Professor Richard S. Sutton, the 2024 Turing Award laureate and widely recognized as the “Father of Reinforcement Learning”, to Shanghai as our lead instructor. We are now openly recruiting and selecting outstanding students and young scholars from both domestic and international universities and research institutes.
一、教学安排与教学目标
暑期学校分为“智能前沿：高级强化学习课程”与“智能先锋：强化学习高级研修班”两个班级：
The Summer School consists of two parallel tracks:
1.高级强化学习课程
“高级强化学习课程”以系统授课与实践项目为主，覆盖函数逼近、on/off-policy学习、策略梯度、GVFs、Oak架构等关键议题，主要面向在校学生，具体报名方式详见后。高级强化学习课程聚焦强化学习的前沿理论与智能体架构，通过大师主课、专题研讨、编程实践与项目实训相结合的方式，帮助学员系统深化对强化学习核心方法及长期研究路线的理解，提升独立开展研究与解决复杂时序决策问题的能力。高级强化学习课程考核方式结合出勤、项目实践、研讨参与及结课成果，将为合格者颁发结课证书。
Intelligence Frontiers: Advanced Reinforcement Learning Course (for students)Focusing on the cutting-edge theories of RL and agent architectures, “Advanced Reinforcement Learning Course, aims to help participants systematically deepen their understanding of core RL methodologies and long-term research roadmaps. Ultimately, it will enhance their capacity to conduct independent research and solve complex sequential decision-making problems. Upon successful completion of all evaluation metrics (including attendance, project execution, and seminar participation), certificates of completion will be awarded.
2.强化学习高级研修班
“强化学习高级研修班”以闭门研讨为核心，围绕Alberta Plan等长期研究方向展开，主要面向相关方向青年学者，采取内部活动与邀请制相结合的方式组织；有意参与者可通过邮箱联系。
Intelligence Pioneers: Advanced Research Seminar on Reinforcement Learning(for scholars, internal & invitation-only). Interested scholars may contact us by email.
二、智能前沿：高级强化学习课程介绍
1.课程时间Time：2026年7月（为期三周，具体时间另行通知）
July 2026, lasting three weeks. The exact schedule will be notified later.
2.课程地点Venue：上海创智学院（上海市徐汇区华发路699弄3号）
Shanghai Innovation Institute (No. 3, Lane 699, Huafa Road, Xuhui District, Shanghai)
3.课程安排 Schedule & Content：每周一、三、五授课（Sutton教授主讲），周二、四安排实践项目，以 Sutton & Barto《Reinforcement Learning: An Introduction》第二版 Part II 及 Chapter 17 为主线。期间还将不定期举办学术冷餐会、前沿启智公开讲座、Poster Session 等多元化交流活动，为学员营造深度互动与思想碰撞的学术氛围。
●Schedule: Mondays, Wednesdays, and Fridays for core lectures (by Prof. Sutton); Tuesdays and Thursdays for practical projects.
●Core Content: This track focuses on systematic lectures and practical projects. Following the roadmap of Part II and Chapter 17 of Reinforcement Learning: An Introduction (2nd Edition) by Sutton & Barto.
●Format: Lectures by Prof. Sutton, TA recitations & coding sessions, group research projects, poster presentations, a final exam, and exclusive office hours with Prof. Sutton. Throughout the program, various high-level academic and social events will be organized, including Academic Buffets/Mixers, Frontier Public Lectures, and Poster Sessions.
三、报名条件与招生规模
1.报名要求 Eligibility：计算机、自动化、数学、统计等相关专业的高年级本科生（大三及以上）、硕士生、博士生等，具备一定的强化学习基础，能参与高强度课程学习。
• Senior undergraduates (3rd year and above), Master’s, and Ph.D. students in Computer Science, Automation, Mathematics, Statistics, or related fields.
• Solid foundation in RL and ability to handle high-intensity coursework.
2.计划人数 Capacity & Distribution：
80-100人
80–100 students
*免学费，交通与用餐自理，上海创智学院可为外地学生提供学生宿舍。
*Tuition-free. Participants shall cover their own transportation and meal expenses. Shanghai Innovation Institute provides student dormitory accommodation for out-of-town students.
四、报名与联系
1.报名时间Application Timeline：
2026年5月27日-6月7日。根据报名情况，可能会安排线上面试，预计六月中旬发出录取邮件。
May 27th, 2026 – June 7th, 2026. The program may arrange online interviews according to application conditions. Admission emails are expected to be sent out in mid-June 2026.
2.报名链接 Application Link：
智能前沿：高级强化学习课程
Advanced Reinforcement Learning Course
https://sii-czxy.feishu.cn/share/base/form/shrcnzD7ehu7GgFqr43iXQGy9hf
3.咨询方式 Contact：
●qcai@sii.edu.cn
●ying.wen@sjtu.edu.cn（if you want to know more information about "Advanced Research Seminar"）
●Richard Sutton 简介
Richard Sutton是计算机科学最高荣誉ACM图灵奖获得者，他在阿尔伯塔大学与Keen Technologies从事人工智能与强化学习算法的教学与设计工作，并担任阿尔伯塔机器智能研究所首席科学顾问及加拿大CIFAR人工智能讲席教授。早年曾就读于斯坦福大学与马萨诸塞大学，先后任职于GTE实验室、AT&T实验室和DeepMind公司。其学术论著被引用约17万次，其中包含强化学习领域的奠基性教材。
