163 citations · 169 across the 8 of their papers we have counts for
10 papers
Ensemble-MIX: Enhancing Sample-Efficiency in Multi-Agent RL via Selective Ensemble-Based Exploration
Tom Danino, Nahum Shimkin
Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more…
Altitude-Loss Optimal Glides in Engine Failure Emergencies -- Accounting for Ground Obstacles and Wind
Daniel Segal, Aharon Bar-Gill, Nahum Shimkin
Engine failure is a recurring emergency in General Aviation and fixed-wing UAVs, often requiring the pilot or remote operator to carry out carefully planned glides to safely reach…
Cooperative Multi-Agent Path Finding: Beyond Path Planning and Collision Avoidance
Nir Greshler, Ofir Gordon, Oren Salzman +1
We introduce the Cooperative Multi-Agent Path Finding (Co-MAPF) problem, an extension to the classical MAPF problem, where cooperative behavior is incorporated. In this setting, a…
ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization
Yair Shemer, Daniel Rotman, Nahum Shimkin
In recent years, there has been an increasing interest in building video summarization tools, where the goal is to automatically create a short summary of an input video that prope…
Learning Control for Air Hockey Striking using Deep Reinforcement Learning
Ayal Taitler, Nahum Shimkin
We consider the task of learning control policies for a robotic mechanism striking a puck in an air hockey game. The control signal is a direct command to the robot's motors. We em…
Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
Oron Anschel, Nir Baram, Nahum Shimkin
Instability and variability of Deep Reinforcement Learning (DRL) algorithms tend to adversely affect their performance. Averaged-DQN is a simple extension to the DQN algorithm, bas…
The Max -Armed Bandit: PAC Lower Bounds and Efficient Algorithms
Yahel David, Nahum Shimkin
We consider the Max -Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time st…
The Max -Armed Bandit: A PAC Lower Bound and tighter Algorithms
Yahel David, Nahum Shimkin
We consider the Max -Armed Bandit problem, where a learning agent is faced with several sources (arms) of items (rewards), and interested in finding the best item overall. At ea…
An Online Convex Optimization Approach to Blackwell's Approachability
Nahum Shimkin
The notion of approachability in repeated games with vector payoffs was introduced by Blackwell in the 1950s, along with geometric conditions for approachability and corresponding…
Response-Based Approachability and its Application to Generalized No-Regret Algorithms
Andrey Bernstein, Nahum Shimkin
Approachability theory, introduced by Blackwell (1956), provides fundamental results on repeated games with vector-valued payoffs, and has been usefully applied since in the theory…