activity
20162022
most citedDiscounted Reinforcement Learning Is Not an Optimization Problem

27 citations · 36 across the 4 of their papers we have counts for

collaborators

6 papers

cs.AI2022

Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have

Nadia M. Ady, Roshan Shariff, Johannes Günther +1

Curiosity for machine agents has been a focus of lively research activity. The study of human and animal curiosity, particularly specific curiosity, has unearthed several propertie…

cs.LG2022

Prototyping three key properties of specific curiosity in computational reinforcement learning

Nadia M. Ady, Roshan Shariff, Johannes Günther +1

Curiosity for machine agents has been a focus of intense research. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that w…

cs.LG20209 cited

Efficient Planning in Large MDPs with Weak Linear Function Approximation

Roshan Shariff, Csaba Szepesvári

Large-scale Markov decision processes (MDPs) require planning algorithms with runtime independent of the number of states of the MDP. We consider the planning problem in MDPs using…

cs.AI201927 cited

Discounted Reinforcement Learning Is Not an Optimization Problem

Abhishek Naik, Roshan Shariff, Niko Yasui +2

Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. It is not an optimization problem in its usual formulat…

cs.LG2018

Differentially Private Contextual Linear Bandits

Roshan Shariff, Or Sheffet

We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a rewa…

stat.ML2016

Conservative Bandits

Yifan Wu, Roshan Shariff, Tor Lattimore +1

We study a novel multi-armed bandit problem that models the challenge faced by a company wishing to explore new strategies to maximize revenue whilst simultaneously maintaining the…