Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits

by   Yunlong Hou, et al.

Motivated by concerns about making online decisions that incur undue amount of risk at each time step, in this paper, we formulate the probably anytime-safe stochastic combinatorial semi-bandits problem. In this problem, the agent is given the option to select a subset of size at most K from a set of L ground items. Each item is associated to a certain mean reward as well as a variance that represents its risk. To mitigate the risk that the agent incurs, we require that with probability at least 1-δ, over the entire horizon of time T, each of the choices that the agent makes should contain items whose sum of variances does not exceed a certain variance budget. We call this probably anytime-safe constraint. Under this constraint, we design and analyze an algorithm PASCombUCB that minimizes the regret over the horizon of time T. By developing accompanying information-theoretic lower bounds, we show under both the problem-dependent and problem-independent paradigms, PASCombUCB is almost asymptotically optimal. Our problem setup, the proposed PASCombUCB algorithm, and novel analyses are applicable to domains such as recommendation systems and transportation in which an agent is allowed to choose multiple items at a single time step and wishes to control the risk over the whole time horizon.


page 1

page 2

page 3

page 4


Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits

A stochastic combinatorial semi-bandit is an online learning problem whe...

Efficient Learning in Large-Scale Combinatorial Semi-Bandits

A stochastic combinatorial semi-bandit is an online learning problem whe...

Constrained regret minimization for multi-criterion multi-armed bandits

We consider a stochastic multi-armed bandit setting and study the proble...

Thompson Sampling Algorithms for Mean-Variance Bandits

The multi-armed bandit (MAB) problem is a classical learning task that e...

Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs

In online learning problems, exploiting low variance plays an important ...

Adaptive sampling method to monitor low-risk pathways with limited surveillance resources

The rise of globalisation has led to a sharp increase in international t...

Safe Disassociation of Set-Valued Datasets

Disassociation introduced by Terrovitis et al. is a bucketization based ...

Please sign up or login with your details

Forgot password? Click here to reset