Alert button
Picture for Shie Mannor

Shie Mannor

Alert button

Reinforcement Learning with Trajectory Feedback

Aug 13, 2020
Yonathan Efroni, Nadav Merlis, Shie Mannor

Figure 1 for Reinforcement Learning with Trajectory Feedback
Viaarxiv icon

Lenient Regret for Multi-Armed Bandits

Aug 10, 2020
Nadav Merlis, Shie Mannor

Figure 1 for Lenient Regret for Multi-Armed Bandits
Figure 2 for Lenient Regret for Multi-Armed Bandits
Figure 3 for Lenient Regret for Multi-Armed Bandits
Viaarxiv icon

Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning

Jul 14, 2020
Shauharda Khadka, Estelle Aflalo, Mattias Marder, Avrech Ben-David, Santiago Miret, Hanlin Tang, Shie Mannor, Tamir Hazan, Somdeb Majumdar

Figure 1 for Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Figure 2 for Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Figure 3 for Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Figure 4 for Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Viaarxiv icon

Bandits with Partially Observable Offline Data

Jun 11, 2020
Guy Tennenholtz, Uri Shalit, Shie Mannor, Yonathan Efroni

Figure 1 for Bandits with Partially Observable Offline Data
Figure 2 for Bandits with Partially Observable Offline Data
Viaarxiv icon

Distributional Robustness and Regularization in Reinforcement Learning

Mar 05, 2020
Esther Derman, Shie Mannor

Viaarxiv icon

Exploration-Exploitation in Constrained MDPs

Mar 04, 2020
Yonathan Efroni, Shie Mannor, Matteo Pirotta

Figure 1 for Exploration-Exploitation in Constrained MDPs
Viaarxiv icon

Stealing Black-Box Functionality Using The Deep Neural Tree Architecture

Feb 23, 2020
Daniel Teitelman, Itay Naeh, Shie Mannor

Figure 1 for Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
Figure 2 for Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
Figure 3 for Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
Figure 4 for Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
Viaarxiv icon

Optimistic Policy Optimization with Bandit Feedback

Feb 19, 2020
Yonathan Efroni, Lior Shani, Aviv Rosenberg, Shie Mannor

Figure 1 for Optimistic Policy Optimization with Bandit Feedback
Viaarxiv icon

Kalman meets Bellman: Improving Policy Evaluation through Value Tracking

Feb 17, 2020
Shirli Di-Castro Shashua, Shie Mannor

Figure 1 for Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
Figure 2 for Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
Figure 3 for Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
Figure 4 for Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
Viaarxiv icon

Tight Lower Bounds for Combinatorial Multi-Armed Bandits

Feb 13, 2020
Nadav Merlis, Shie Mannor

Figure 1 for Tight Lower Bounds for Combinatorial Multi-Armed Bandits
Figure 2 for Tight Lower Bounds for Combinatorial Multi-Armed Bandits
Figure 3 for Tight Lower Bounds for Combinatorial Multi-Armed Bandits
Viaarxiv icon