N. Shimkin

activity

20132025

most citedAveraged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning

163 citations · 169 across the 8 of their papers we have counts for

collaborators

Showing stat.MLShow all

2 papers · 1 filter

stat.ML2015

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

Yahel David, Nahum Shimkin

We consider the Max $K$ -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…

stat.ML2015★ 1 cited

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

Yahel David, Nahum Shimkin

We consider the Max $K$ -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…

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

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

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

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