4 citations · 17 across the 9 of their papers we have counts for
8 papers · 1 filter
Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
Ronshee Chawla, Daniel Vial, Sanjay Shakkottai +1
The study of collaborative multi-agent bandits has attracted significant attention recently. In light of this, we initiate the study of a new collaborative setting, consisting of $…
Minimax Regret for Cascading Bandits
Daniel Vial, Sujay Sanghavi, Sanjay Shakkottai +1
Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting. For the case of unstructured rewards, w…
Robust Multi-Agent Bandits Over Undirected Graphs
Daniel Vial, Sanjay Shakkottai, R. Srikant
We consider a multi-agent multi-armed bandit setting in which honest agents collaborate over a network to minimize regret but malicious agents can disrupt learning arbitrar…
Improved Algorithms for Misspecified Linear Markov Decision Processes
Daniel Vial, Advait Parulekar, Sanjay Shakkottai +1
For the misspecified linear Markov decision process (MLMDP) model of Jin et al. [2020], we propose an algorithm with three desirable properties. (P1) Its regret after episodes…
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Daniel Vial, Advait Parulekar, Sanjay Shakkottai +1
We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP). Under minimal assumptions, it obtains sublinear regret, is computationally…
One-bit feedback is sufficient for upper confidence bound policies
Daniel Vial, Sanjay Shakkottai, R. Srikant
We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards…
Robust Multi-Agent Multi-Armed Bandits
Daniel Vial, Sanjay Shakkottai, R. Srikant
Recent works have shown that agents facing independent instances of a stochastic -armed bandit can collaborate to decrease regret. However, these works assume that each agent al…
Empirical Policy Evaluation with Supergraphs
Daniel Vial, Vijay Subramanian
We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value one…