New algorithms improve exploration in unbounded reward settings.
problem Challenges in exploration with unbounded rewards in reinforcement learning.
method Proposed EXP4.P and EXP4-RL algorithms for unbounded reward settings.
result EXP4.P achieves global optimality in linear cases with one competent expert.
New algorithm tackles adversarial contextual bandits using stochastic smoothing.
problem Adversarial contextual bandit problems.
method Stochastic smoothing perspective and random perturbation based algorithms.
result Zero-order bound of O ( T ) O(\sqrt{T}) O ( T ) and first-order bound of O ( L T ∗ 2 / 3 ) O(L^{*2/3}_{T}) O ( L T ∗ 2/3 ) for the proposed algorithm. Improved regret bounds for bandits with fixed expert advice using information theory.
problem Optimizing regret in bandit problems with fixed expert distributions.
method Information-theoretic analysis and KL-divergence measures.
result First regret bounds for EXP4 that can get arbitrarily close to zero under certain conditions.
New algorithm improves cache management with delayed feedback and decaying costs.
problem Improving cache replacement policies with delayed and decaying costs feedback.
method Proposed EXP4-DFDC adaptive reinforcement learning algorithm.
result Expected regret is a vanishing quantity as a function of time.
New algorithm bounds regret in mediator feedback bandit problems.
problem Mediator feedback bandit game with policy sets.
method Adopting EXP4 algorithm, new regret bounds based on policy set capacity.
result Nearly-matching lower bounds for policy set families.
Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.
problem Maximizing reward by choosing actions sequentially from a set of experts.
method Proposed a variant of Exp4.P for infinitely many experts and a meta-algorithm.
result Proved high-probability upper bound of i l d e O ( i ∗ K + K T ) ilde{\mathcal{O}} \big( i^*K + \sqrt{KT} \big) i l d e O ( i ∗ K + K T ) on regret. A new algorithm reduces inference error in adaptive contextual bandits.
problem Challenges in statistical inference for adaptive contextual bandits.
method Proposes a regularized EXP4 algorithm that satisfies the Lai-Wei stability condition.
result Valid Wald-type confidence intervals for linear functionals can be achieved without the price of adaptivity.
We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…
New algorithm reduces sleeping bandits' regret to O(sqrt(T)).
problem Improving sleeping bandits with stochastic actions and adversarial rewards.
method Inspired by EXP3, new algorithm with O ( T ) O(\sqrt{T}) O ( T ) regret. result Achieves O ( T ) O(\sqrt{T}) O ( T ) regret, improving over existing O ( T 2 / 3 ) O(T^{2/3}) O ( T 2/3 ) . Improves reward bounds for prediction with expert advice using abstention.
problem Prediction with expert advice under bandit feedback with abstention.
method CBA algorithm exploiting abstention to improve reward bounds.
result Achieved significant improvement in reward bounds for general confidence-rated predictors.
Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit algorithms for non-stationary environments by equipping existing methods for i.i.d. …
Near-optimal per-action regret bounds for sleeping bandits are derived.
problem Optimizing performance in sleeping bandits where arms and losses are chosen by an adversary.
method Directly minimizing per-action regret using generalized versions of EXP3, EXP3-IX, and FTRL with Tsallis entropy.
result Near-optimal bounds of order O ( T A ln K ) O(\sqrt{TA\ln{K}}) O ( T A ln K ) and O ( T A K ) O(\sqrt{T\sqrt{AK}}) O ( T A K ) are obtained.