Alert button
Picture for Tom Zahavy

Tom Zahavy

Alert button

Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces

May 23, 2019
Chen Tessler, Tom Zahavy, Deborah Cohen, Daniel J. Mankowitz, Shie Mannor

Figure 1 for Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
Figure 2 for Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
Figure 3 for Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
Figure 4 for Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces
Viaarxiv icon

Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies

Feb 26, 2019
Tom Zahavy, Avinatan Hasidim, Haim Kaplan, Yishay Mansour

Figure 1 for Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
Figure 2 for Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
Figure 3 for Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
Figure 4 for Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
Viaarxiv icon

Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching

Jan 24, 2019
Tom Zahavy, Shie Mannor

Figure 1 for Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
Figure 2 for Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
Figure 3 for Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
Figure 4 for Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching
Viaarxiv icon

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Sep 06, 2018
Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor

Figure 1 for Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Figure 2 for Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Figure 3 for Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Figure 4 for Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Viaarxiv icon

Deep Learning Reconstruction of Ultra-Short Pulses

Mar 15, 2018
Tom Zahavy, Alex Dikopoltsev, Oren Cohen, Shie Mannor, Mordechai Segev

Figure 1 for Deep Learning Reconstruction of Ultra-Short Pulses
Figure 2 for Deep Learning Reconstruction of Ultra-Short Pulses
Figure 3 for Deep Learning Reconstruction of Ultra-Short Pulses
Figure 4 for Deep Learning Reconstruction of Ultra-Short Pulses
Viaarxiv icon

Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies

Mar 13, 2018
Tom Zahavy, Avinatan Hasidim, Haim Kaplan, Yishay Mansour

Figure 1 for Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies
Figure 2 for Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies
Figure 3 for Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies
Viaarxiv icon

Train on Validation: Squeezing the Data Lemon

Feb 16, 2018
Guy Tennenholtz, Tom Zahavy, Shie Mannor

Figure 1 for Train on Validation: Squeezing the Data Lemon
Figure 2 for Train on Validation: Squeezing the Data Lemon
Figure 3 for Train on Validation: Squeezing the Data Lemon
Figure 4 for Train on Validation: Squeezing the Data Lemon
Viaarxiv icon

Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms

Nov 05, 2017
Tom Zahavy, Bingyi Kang, Alex Sivak, Jiashi Feng, Huan Xu, Shie Mannor

Figure 1 for Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms
Figure 2 for Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms
Figure 3 for Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms
Figure 4 for Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms
Viaarxiv icon

Shallow Updates for Deep Reinforcement Learning

Nov 02, 2017
Nir Levine, Tom Zahavy, Daniel J. Mankowitz, Aviv Tamar, Shie Mannor

Figure 1 for Shallow Updates for Deep Reinforcement Learning
Figure 2 for Shallow Updates for Deep Reinforcement Learning
Figure 3 for Shallow Updates for Deep Reinforcement Learning
Figure 4 for Shallow Updates for Deep Reinforcement Learning
Viaarxiv icon

Graying the black box: Understanding DQNs

Apr 24, 2017
Tom Zahavy, Nir Ben Zrihem, Shie Mannor

Figure 1 for Graying the black box: Understanding DQNs
Figure 2 for Graying the black box: Understanding DQNs
Figure 3 for Graying the black box: Understanding DQNs
Figure 4 for Graying the black box: Understanding DQNs
Viaarxiv icon