Programs
Fall 2020

Theory of Reinforcement Learning

Aug. 19Dec. 18, 2020

Because of the uncertainty caused by COVID-19, it is still unclear if this program will take place in person or online only. This page will be updated as soon as we have more information.

This program aims to advance the theoretical foundations of reinforcement learning (RL) and foster new collaborations between researchers across RL and computer science.

Recent years have seen a surge of interest in reinforcement learning, fueled by exciting new applications of RL techniques to various problems in artificial intelligence, robotics, and natural sciences. Many of these advances were made possible by a combination of large-scale computation, innovative use of flexible neural network architectures and training methods, and new and classical RL algorithms. However, we lack a solid understanding of when, why, and to what extent these algorithms work.

Reinforcement learning's core issues, such as efficiency of exploration and the trade-off between the scale and the difficulty of learning and planning, have received concerted study over the last few decades within many disciplines and communities, including computer science, numerical analysis, artificial intelligence, control theory, operations research, and statistics. The result has been a solid body of work that has built and resolved some of the core problems; yet, the most pressing problems, concerning how one can design highly scalable algorithms, still remain open.

This program aims to reunite researchers across disciplines that have played a role in developing the theory of reinforcement learning. It will review past developments and identify promising directions of research, with an emphasis on addressing existing open problems, ranging from the design of efficient, scalable algorithms for exploration to how to control learning and planning. It also aims to deepen the understanding of model-free vs. model-based learning and control, and the design of efficient methods to exploit structure and adapt to easier environments.

sympa [at] lists.simons.berkeley.edu (body: subscribe%20rl2020announcements%40lists.simons.berkeley.edu) (Click here to subscribe to our announcements email list for this program).

Organizers:

Csaba Szepesvari (University of Alberta, Google DeepMind; chair), Emma Brunskill (Stanford University), Sébastien Bubeck (Microsoft Research; Visiting Scientist and Program Organizer), Alan Malek (DeepMind), Sean Meyn (University of Florida), Ambuj Tewari (University of Michigan), Mengdi Wang (Princeton University)

Long-Term Participants (including Organizers):

Yasin Abbasi-Yadkori (DeepMind), Pieter Abbeel (UC Berkeley), Rediet Abebe (Harvard University), David Abel (Research Scientist, DeepMind), Raman Arora (Johns Hopkins University), Yu Bai (Salesforce Research), Peter Bartlett (Simons Institute, UC Berkeley), Vivek Shripad Borkar (Indian Institute of Technology Bombay), Emma Brunskill (Stanford University), Sébastien Bubeck (Microsoft Research; Visiting Scientist and Program Organizer), Ciara Pike-Burke (Imperial College London), Ana Bušić (INRIA), Marco Campi (University of Brescia), Rene Carmona (Princeton University), Marco Dalai (University of Brescia), Anca Dragan (UC Bekeley), Sumitra Ganesh (JP Morgan), Mohammad Ghavamzadeh (Google Research), Quanquan Gu (University of California, Los Angeles), Anupam Gupta (Carnegie Mellon University), Andras Gyorgy (DeepMind), Nika Haghtalab (Cornell University), Niao He (University of Illinois at Urbana-Champaign), Rahul Jain (University of Southern California), Nan Jiang (University of Illinois at Urbana-Champaign), Chi Jin (Princeton University), Michael Jordan (UC Berkeley), Mihailo Jovanovic (University of Southern California), Amin Karbasi (Yale University), Wouter Koolen (Centrum Wiskunde & Informatica), Akshay Krishnamurthy (Microsoft Research; Visiting Scientist), Tor Lattimore (), Jason Lee (Princeton University), Sergey Levine (UC Berkeley), Lihong Li (Google Brain; Visiting Scientist), Tengyu Ma (Stanford University), Siva Theja Maguluri (Georgia Institute of Technology), Sean Meyn (University of Florida), Eric Moulines (Ecole Polytechnique), Seffi Naor (Technion - Israel Institute of Technology), Angelia Nedich (Arizona State University), Gergely Neu (UPF), Erol A. Peköz (Boston University), Marek Petrik (University of New Hampshire), Benjamin Recht (UC Berkeley), Daniel Russo (Columbia University), Barna Saha (UC Berkeley), Shankar Sastry (UC Berkeley), Bruno Scherrer (INRIA), Dale Schuurmans (University of Alberta), Aaron Sidford (Stanford University), Csaba Szepesvari (University of Alberta, Google DeepMind; chair), Matus Telgarsky (University of Illinois, Urbana-Champaign), Ambuj Tewari (University of Michigan), Claire Tomlin (UC Berkeley), Mathukumalli Vidyasagar (IIT Hyderabad), Stefan Wager (Stanford Graduate School of Business), Martin Wainwright (UC Berkeley), Mengdi Wang (Princeton University), Huizhen Yu (University of Alberta)

Research Fellows:

Jalaj Bhandari (Columbia University), Lin Chen (Yale University), Vidya Muthukumar (UC Berkeley; Google Research Fellow), Mohamad Kazem Shirani Faradonbeh (University of Florida), Zhaoran Wang (Northwestern University), Lin Yang (University of California, Los Angeles; Facebook/Novi Research Fellow), Zhuoran Yang (Princeton University; VMware Research Fellow), Christina Yu (Cornell University)

Visiting Graduate Students and Postdocs:

Kumar Krishna Agrawal (UC Berkeley), Philip Amortila (University of Illinois at Urbana-Champaign), Gabor Balazs (), Kush Bhatia (UC Berkeley), Shantanu Prasad Burnwal (IIT Hyderabad), Michael Chang (UC Berkeley), Niladri Chatterji (UC Berkeley), Jinglin Chen (University of Illinois at Urbana-Champaign), Zixiang Chen (UCLA), Daniela Cialfi (University of CHIETI-PESCARA), Xiaowu Dai (UC Berkeley), Gokce Dayanikli (Princeton University), Dylan Foster (Massachusetts Institute of Technology (MIT)), Germano Gabbianelli (Universitat Pompeu Fabra), Thomas Gilbert (UC Berkeley), Botao Hao (Princeton University), Jiafan He (UCLA), Haque Ishfaq (McGill University), Yujia Jin (Stanford University), Pritish Kamath (Toyota Technological Institute at Chicago), Seri Khoury (UC Berkeley), Michael Kim (UC Berkeley), Michael Konobeev (University of Alberta), Kshitij Kulkarni (UC Berkeley), Gene Li (Toyota Technological Institute at Chicago), Junchi Li (UC Berkeley), Yao Liu (Stanford), Jincheng Mei (University of Alberta), Aditya Modi (University of Michigan, Ann Arbor), Aldo Pacchiano (UC Berkeley), Juan Perdomo (UC Berkeley), Sudeep Raja (Columbia University), Sergey Samsonov (National Research University Higher School of Economics), Roshan Shariff (University of Alberta), Sean Sinclair (Cornell University), Sharan Vaswani (MILA), Ruosong Wang (Carnegie Mellon University), Chen-Yu Wei (University of Southern California), Gellert Weisz (DeepMind), Tengyang Xie (University of Illinois at Urbana-Champaign), Andrea Zanette (Stanford University), Kaiqing Zhang (UIUC), Dongruo Zhou (UCLA)

Workshops

Aug. 31Sep. 4, 2020

Organizers:

Csaba Szepesvari (University of Alberta, Google DeepMind; chair), Emma Brunskill (Stanford University), Sébastien Bubeck (MSR), Alan Malek (DeepMind), Sean Meyn (University of Florida), Ambuj Tewari (University of Michigan), Mengdi Wang (Princeton)
Sep. 28Oct. 2, 2020

Organizers:

Lihong Li (Google Brain; chair), Marc G. Bellemare (Google Brain)
Oct. 26Oct. 30, 2020

Organizers:

Shipra Agrawal (Columbia University; chair), Sébastien Bubeck (MSR), Alan Malek (DeepMind)
Nov. 30Dec. 4, 2020

Organizers:

Mengdi Wang (Princeton; chair), Emma Brunskill (Stanford University), Sean Meyn (University of Florida)

Those interested in participating in this program should send an email to the organizers rl2020 [at] lists.simons.berkeley.edu (at this address).

 Subscribe to the program calendar.

Internal Program Activities

Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Tuesday, November 17 10:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Tuesday, November 3 10:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Thursday, October 29 1:00 pm2:00 pm
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Thursday, October 22 1:00 pm2:00 pm
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Thursday, October 15 1:00 pm2:00 pm
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Friday, September 25 9:00 am11:00 am
Thursday, September 24 1:00 pm2:00 pm
Wednesday, September 23 11:00 am12:00 pm
Wednesday, September 23 9:00 am11:00 am
Tuesday, September 22 10:00 am11:00 am
Friday, September 18 11:00 am12:00 pm
Friday, September 18 9:30 am10:00 am
Friday, September 18 9:00 am9:30 am
Thursday, September 17 1:00 pm2:00 pm
Thursday, September 10 1:00 pm2:00 pm
Thursday, August 27 1:00 pm1:45 pm