Reinforcement Learning for Real Life Virtual Conference (June 27-28, 2020)
Check official website for updates: https://sites.google.com/view/RL4RealLife
Time & Schedule
Atlantic Run: SF 9am-12pm, Boston 12–3pm, London 5–8pm, Paris 6–9pm, Bangalore 9:30pm-0:30am. June 27
Pacific Run: SF 6–9pm, Boston 9pm-12am, Tokyo/Sydney 10am-1pm, Beijing 9am-12pm, Bangalore 6:30–9:30am. June 27 (SF/Boston) / June 28 (Tokyo/Sydney/Beijing/Bangalore)
Schedule (for each of two runs)
Time 0:00–1:00 panel discussion / Q&A (wrt to local starting time)
Time 1:00–3:00 crowd-postering
Invited Speakers / Panelists
Atlantic Run, SF 9am-12pm June 27, RL+healthcare
- Finale Doshi-Velez, Harvard
- Niranjani Prasad, Princeton
- Suchi Saria, JHU
- Moderator:Susan Murphy, Harvard
- Chair: Omer Gottesman, Harvard
- Ask/vote questions to panelists.
Pacific Run SF 6–9pm June 27, general topic
- Ed Chi, Google
- Chelsea Finn, Stanford
- Jason Gauci, Facebook
- Moderator: Peter Stone, UT Austin & Sony AI
- Chair: Lihong Li, Google
- Ask/vote questions to panelists.
We will request invited speakers and moderators to share their expertise w.r.t. the real life aspects of RL, with pre-recorded videos. We create polls for the audience to submit questions for the panel.
Mission
Reinforcement learning (RL) is a general learning, predicting, and decision making paradigm and applies broadly in science, engineering and arts. RL has seen prominent successes in many problems, such as Atari games, AlphaGo, robotics, recommender systems, and AutoML. However, applying RL in the real world remains challenging, and a natural question is:
What are the issues and how to solve them?
The main goals of the conference are to: (1) identify key research problems that are critical for the success of real-world applications; (2) report progress on addressing these critical issues; and (3) have practitioners share their success stories of applying RL to real-world problems, and the insights gained from the applications.
We invite poster discussions successfully applying RL algorithms to real-life problems by addressing practically relevant RL issues. Our topics of interest are general, including but not limited to topics below:
- Practical RL algorithms, which covers all algorithmic challenges of RL, especially those that directly address challenges faced by real-world applications;
- Practical issues: generalization, sample/time/space efficiency, exploration vs. exploitation, reward specification and shaping, scalability, model-based learning (model validation and model error estimation), prior knowledge, safety, accountability, interpretability, reproducibility, hyper-parameter tuning;
Applications: advertisements, autonomous driving, business, chemical synthesis, conversational AI, drawing, drug design, education, energy, finance, healthcare, industrial control, music, recommender systems, robotics, transportation, or other problems in science, engineering and arts.
Paper submission
Deadline: June 15, 2020
Notification: June 21, 2020
Submission website
We will do a quick screening of paper submissions. We welcome submissions of recently published work. Authors pre-record videos (with Slideslive), host their own video conferencing channels (with Zoom/Google Hangout).
Communication
Real-time Text-based Chat
Authors of posters can create their own topics. Audience can have discussions before/during/after the virtual conference. Organizers can make announcements.
Welcome to join our Slack Workspace for RL for Real Life.
Virtual Booths
We encourage participants to host virtual booths to discuss research topics, to look for job opportunities, to social, etc.
Twitter #RL4RealLife
Contact by email yuxili@gmail.com
Co-Chairs
- Gabriel Dulac-Arnold (Google Research)
- Alborz Geramifard (Facebook AI)
- Omer Gottesman (Harvard)
- Lihong Li (Google Research)
- Yuxi Li (Attain.ai)
- Anusha Nagabandi (UC Berkeley & Google)
- Zhiwei (Tony) Qin (Didi)
- Csaba Szepesvari (Deepmind & U. of Alberta)