Picture for Nahum Shimkin

Nahum Shimkin

Cooperative Multi-Agent Path Finding: Beyond Path Planning and Collision Avoidance

Add code
May 23, 2021
Figure 1 for Cooperative Multi-Agent Path Finding: Beyond Path Planning and Collision Avoidance
Figure 2 for Cooperative Multi-Agent Path Finding: Beyond Path Planning and Collision Avoidance
Figure 3 for Cooperative Multi-Agent Path Finding: Beyond Path Planning and Collision Avoidance
Figure 4 for Cooperative Multi-Agent Path Finding: Beyond Path Planning and Collision Avoidance
Viaarxiv icon

ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization

Add code
Dec 08, 2019
Figure 1 for ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization
Figure 2 for ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization
Figure 3 for ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization
Figure 4 for ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization
Viaarxiv icon

Learning Control for Air Hockey Striking using Deep Reinforcement Learning

Add code
Apr 25, 2017
Figure 1 for Learning Control for Air Hockey Striking using Deep Reinforcement Learning
Figure 2 for Learning Control for Air Hockey Striking using Deep Reinforcement Learning
Figure 3 for Learning Control for Air Hockey Striking using Deep Reinforcement Learning
Figure 4 for Learning Control for Air Hockey Striking using Deep Reinforcement Learning
Viaarxiv icon

Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning

Add code
Mar 10, 2017
Figure 1 for Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
Figure 2 for Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
Figure 3 for Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
Figure 4 for Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
Viaarxiv icon

The Max $K$-Armed Bandit: PAC Lower Bounds and Efficient Algorithms

Add code
Dec 23, 2015
Viaarxiv icon

The Max $K$-Armed Bandit: A PAC Lower Bound and tighter Algorithms

Add code
Aug 23, 2015
Viaarxiv icon

An Online Convex Optimization Approach to Blackwell's Approachability

Add code
Mar 01, 2015
Viaarxiv icon

Response-Based Approachability and its Application to Generalized No-Regret Algorithms

Add code
Dec 30, 2013
Viaarxiv icon