25 citations · 177 across the 40 of their papers we have counts for
6 papers · 1 filter
Actor-Critic based Improper Reinforcement Learning
Mohammadi Zaki, Avinash Mohan, Aditya Gopalan +1
We consider an improper reinforcement learning setting where a learner is given base controllers for an unknown Markov decision process, and wishes to combine them optimally to…
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury +1
We present a non-asymptotic lower bound on the eigenspectrum of the design matrix generated by any linear bandit algorithm with sub-linear regret when the action set has well-behav…
Does DQN Learn?
Aditya Gopalan, Gugan Thoppe
A primary requirement for any reinforcement learning method is that it should produce policies that improve upon the initial guess. In this work, we show that the widely used Deep…
Minimum mean-squared error estimation with bandit feedback
Ayon Ghosh, L. A. Prashanth, Dipayan Sen +1
We consider the problem of sequentially learning to estimate, in the mean squared error (MSE) sense, a Gaussian -vector of unknown covariance by observing only of its en…
A Framework for Blockchain Architecture Design
Partha S. Dey, Aditya Gopalan
Emerging applications of blockchains, such as grocery supply chains, require frequent updates to the data structure. This is in contrast with typical analyses of the Bitcoin blockc…
Bregman Deviations of Generic Exponential Families
Sayak Ray Chowdhury, Patrick Saux, Odalric-Ambrym Maillard +1
We revisit the method of mixture technique, also known as the Laplace method, to study the concentration phenomenon in generic exponential families. Combining the properties of Bre…