NOTE: Subscription is free, but mandatory (meeting link will be sent to registered participants): Subscribe.

An email with a Zoom link was sent to all registered participants (if you are a participant and did not receive an email please check your spam folder).

The meeting will be recorded and uploaded online a few days after the event.

We thank all the speakers and participants. A full recording of the event is given in IRLD2021 recording .

If you have feedback regarding the event, feel free to fill it in the following form: IRLD2021 feedback .

For issues contact: IsraelRLday@gmail.com.

We are thrilled to announce the first Israeli Reinforcement Learning Day, an academic meetup of researchers and practitioners of Reinforcement Learning in Israeli academia and industry. The event will take place virtually on Wednesday 7/4/2021, and will include talks by invited speakers and short presentations of recent work in the field by Israeli researchers.

Schedule

8:55-9:00	IRLD organizers - Opening remarks
9:00-9:30	Guy Tenenholtz - Offline Reinforcement Learning (Tutorial)
9:30-9:50	Daniel Mankowitz - Challenges of Real World Reinforcement Learning
9:50-10:00	Break
10:00-10:50	Session 1
	Hanan Shteingart - The Business Value of Reinforcement Learning and Causal Inference
	Ran Levy - Call Assignment in Cellular Networks with Vehicular Relay Nodes
	Binyamin Manela - Bias-Reduced Hindsight Experience Replay with Virtual Goal
	Dean Zadok - Modeling Affect-based Intrinsic Rewards for Exploration and Learning
10:50-11:00	Break
11:00-11:45	Keynote speaker: Aviv Tamar
11:45-12:10	Session 2
	Gal Dalal - Acting in Delayed Environments with Non-Stationary Markov Policies
	Yonathan Efroni - Confidence-Budget Matching for Sequential Budgeted Learning
12:10-13:10	Break
13:10-13:55	Keynote speaker: Shie Mannor
13:55-14:20	Session 3
	Lior Shani - Online Apprenticeship Learning
	Asaf Cassel - Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret
14:20-14:30	Break
14:30-15:15	Keynote speaker: Yishay Mansour
15:15-15:40	Session 4
	Oren Peer - Ensemble Bootstrapping for Q-Learning
	Shadi Endrawis - Efficient Self-Supervised Data Collection for Offline Robot Learning
15:40-15:50	Break
15:50-16:40	Session 5
	Carmel Rabinovitz - Unsupervised Feature Learning for Manipulation with Contrastive Domain Randomization
	Dan Kushnir - Impact-driven Exploration with Contrastive Unsupervised Representations
	Alap Kshirsagar - Evaluating Guided Policy Search for Human-Robot Handovers
16:40-17:10	Tom Zahavy - Meta-gradient Reinforcement Learning (Tutorial)

Subscription is free, but mandatory: Subscribe.

For any questions or proposals contact IsraelRLday@gmail.com.

Invited Speakers

Aviv Tamar	Shie Mannor	Yishay Mansour
Technion	Technion & NVIDIA	TAU & Google

Organizers

Aviv Rosenberg	Assaf Hallak	Orr Krupnik	Tom Jurgenson
TAU	NVIDIA	Technion	Technion