Picture for Balazs Szorenyi

Balazs Szorenyi

A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound

Add code
Dec 04, 2019
Figure 1 for A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound
Figure 2 for A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound
Figure 3 for A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound
Viaarxiv icon

Learning to Crawl

Add code
May 29, 2019
Figure 1 for Learning to Crawl
Figure 2 for Learning to Crawl
Figure 3 for Learning to Crawl
Figure 4 for Learning to Crawl
Viaarxiv icon

Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning

Add code
Jun 04, 2018
Figure 1 for Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning
Figure 2 for Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning
Figure 3 for Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning
Figure 4 for Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning
Viaarxiv icon

Multi-objective Bandits: Optimizing the Generalized Gini Index

Add code
Jun 15, 2017
Figure 1 for Multi-objective Bandits: Optimizing the Generalized Gini Index
Figure 2 for Multi-objective Bandits: Optimizing the Generalized Gini Index
Figure 3 for Multi-objective Bandits: Optimizing the Generalized Gini Index
Viaarxiv icon

Distributed Clustering of Linear Bandits in Peer to Peer Networks

Add code
Jun 07, 2016
Figure 1 for Distributed Clustering of Linear Bandits in Peer to Peer Networks
Figure 2 for Distributed Clustering of Linear Bandits in Peer to Peer Networks
Viaarxiv icon