activity
20182026
most citedRethinking Knowledge Transfer in Learning Using Privileged Information

2 citations · 3 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20242 cited

Rethinking Knowledge Transfer in Learning Using Privileged Information

Danil Provodin, Bram van den Akker, Christina Katsimerou +2

In supervised machine learning, privileged information (PI) is information that is unavailable at inference, but is accessible during training time. Research on learning using priv…

cs.LG2024

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling

Danil Provodin, Maurits Kaptein, Mykola Pechenizkiy

We present a new algorithm based on posterior sampling for learning in Constrained Markov Decision Processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achi…

cs.LG2023

Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need

Danil Provodin, Pratik Gajane, Mykola Pechenizkiy +1

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achi…

cs.LG2022

An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning

Danil Provodin, Pratik Gajane, Mykola Pechenizkiy +1

We study a posterior sampling approach to efficient exploration in constrained reinforcement learning. Alternatively to existing algorithms, we propose two simple algorithms that a…

cs.LG2021

The Impact of Batch Learning in Stochastic Bandits

Danil Provodin, Pratik Gajane, Mykola Pechenizkiy +1

We consider a special case of bandit problems, namely batched bandits. Motivated by natural restrictions of recommender systems and e-commerce platforms, we assume that a learning…

cs.LG2018

Maximum likelihood estimation of a finite mixture of logistic regression models in a continuous data stream

Maurits Kaptein, Paul Ketelaar

In marketing we are often confronted with a continuous stream of responses to marketing messages. Such streaming data provide invaluable information regarding message effectiveness…