Timezone: »

The Challenges of Real World Reinforcement Learning
Daniel Mankowitz · Gabriel Dulac-Arnold · Shie Mannor · Omer Gottesman · Anusha Nagabandi · Doina Precup · Timothy A Mann

@ None
Event URL: https://sites.google.com/view/neurips2020rwrl »

Reinforcement Learning (RL) has had numerous successes in recent years in solving complex problem domains. However, this progress has been largely limited to domains where a simulator is available or the real environment is quick and easy to access. This is one of a number of challenges that are bottlenecks to deploying RL agents on real-world systems. Two recent papers identify nine important challenges that, if solved, will take a big step towards enabling RL agents to be deployed to real-world systems (Dulac et. al. 2019, 2020).The goals of this workshop are four-fold: (1) Providing a forum for researchers in academia, industry researchers as well as industry practitioners from diverse backgrounds to discuss the challenges faced in real-world systems; (2) discuss and prioritize the nine research challenges. This includes determining which challenges we should focus on next, whether any new challenges should be added to the list or existing ones removed from this list; (3) Discuss problem formulations for the various challenges and critique these formulations or develop new ones. This is especially important for more abstract challenges such as explainability. We should also be asking ourselves whether the current Markov Decision Process (MDP) formulation is sufficient for solving these problems or whether modifications need to be made. (4) Discuss approaches to solving combinations of these challenges.

Sat 8:30 a.m. - 8:40 a.m. [iCal]
Introduction and Overview (Introduction) [ Video ]
Daniel Mankowitz
Sat 8:40 a.m. - 9:20 a.m. [iCal]
Keynote: Aviv Tamar (Talk) [ Video ]
Aviv Tamar
Sat 9:20 a.m. - 10:00 a.m. [iCal]
Keynote: Emma Brunskill (Talk) [ Video ]
Emma Brunskill
Sat 10:00 a.m. - 10:40 a.m. [iCal]
Keynote: Jost Tobias Springenberg (Talk) [ Video ]
Jost Tobias Springenberg
Sat 10:40 a.m. - 11:20 a.m. [iCal]
Mini-panel discussion 1 - Bridging the gap between theory and practice (Discussion Panel)
Aviv Tamar, Emma Brunskill, Jost Tobias Springenberg, Daniel Mankowitz
Sat 11:20 a.m. - 11:50 a.m. [iCal]
Poster session 1 (Poster Session and Coffee Break)
Sat 11:50 a.m. - 12:30 p.m. [iCal]
Keynote: Franziska Meier (Talk)
Sat 12:30 p.m. - 1:10 p.m. [iCal]

The two speakers do not have Neurips profiles. There emails are: Scott Kuindersma - skuindersma@bostondynamics.com (Probably the main speaker) Marc Reibert - marcraibert@bostondynamics.com (Probably not going to speak)

Sat 1:10 p.m. - 1:50 p.m. [iCal]

The following speakers that will be at this event do not have Neurips profiles: Franziska Meier - fmeier@fb.com Marc Reibert - marcraibert@bostondynamics.com Scott Kuindersma - skuindersma@bostondynamics.com

Timothy A Mann
Sat 1:50 p.m. - 3:20 p.m. [iCal]
Lunch (Lunch Break)
Sat 3:20 p.m. - 4:00 p.m. [iCal]

Spotlight talks will be 4 talks of selected papers - These will be confirmed on October 31st.

Sat 4:00 p.m. - 4:40 p.m. [iCal]
Keynote: Tom Diettrich (Talk) [ Video ]
Tom Dietterich
Sat 4:40 p.m. - 5:20 p.m. [iCal]
Keynote: Chelsea Finn (Talk) [ Video ]
Chelsea Finn
Sat 5:20 p.m. - 6:00 p.m. [iCal]
Mini-panel discussion 3 - Prioritizing Real World RL Challenges (Discussion Panel)
Chelsea Finn, Tom Dietterich, Gabriel Dulac-Arnold
Sat 6:00 p.m. - 6:30 p.m. [iCal]
Poster session 2 (Poster Session and Coffee Break)
Sat 6:30 p.m. - 7:10 p.m. [iCal]
Keynote: Angela Schoellig (Talk) [ Video ]
Angela Schoellig
Sat 7:10 p.m. - 7:50 p.m. [iCal]
Keynote: Anca Dragan (Talk) [ Video ]
Anca Dragan
Sat 7:50 p.m. - [iCal]

Please also add: Omer Gottesman - omer_gottesman@brown.edu

Anca Dragan, Angela Schoellig, Anusha Nagabandi

Author Information

Daniel Mankowitz (DeepMind)
Gabriel Dulac-Arnold (Google Research)
Shie Mannor (Technion)
Omer Gottesman (Harvard)
Anusha Nagabandi (UC Berkeley)
Doina Precup (DeepMind)
Timothy A Mann (DeepMind)

More from the Same Authors