activity
20182023
most citedDistribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards

18 citations · 24 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2023

Best Arm Identification in Bandits with Limited Precision Sampling

Kota Srinivas Reddy, P. N. Karthik, Nikhil Karamchandani +1

We study best arm identification in a variant of the multi-armed bandit problem where the learner has limited precision in arm selection. The learner can only sample arms via certa…

cs.LG2022★ 1 cited

Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget

Fathima Zarin Faizal, Jayakrishnan Nair

We consider a constrained, pure exploration, stochastic multi-armed bandit formulation under a fixed budget. Each arm is associated with an unknown, possibly multi-dimensional dist…

cs.LG2021

Optimal Cycling of a Heterogenous Battery Bank via Reinforcement Learning

Vivek Deulkar, Jayakrishnan Nair

We consider the problem of optimal charging/discharging of a bank of heterogenous battery units, driven by stochastic electricity generation and demand processes. The batteries in…

cs.LG2020★ 3 cited

Bandit algorithms: Letting go of logarithmic regret for statistical robustness

Kumar Ashutosh, Jayakrishnan Nair, Anmol Kagrecha +1

We study regret minimization in a stochastic multi-armed bandit setting and establish a fundamental trade-off between the regret suffered under an algorithm, and its statistical ro…

cs.LG2019★ 18 cited

Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards

Anmol Kagrecha, Jayakrishnan Nair, Krishna Jagannathan

Classical multi-armed bandit problems use the expected value of an arm as a metric to evaluate its goodness. However, the expected value is a risk-neutral metric. In many applicati…