arXiv research

New algorithm reduces high-probability regret for time-varying feedback graphs.

New approach for online learning with adaptive adversaries, simpler and more effective.

New algorithms achieve high-probability parameter-free regret in online convex optimization with heavy-tailed data.

New method minimizes regret in AMDP with high probability.

ES reduces high-probability regret in stochastic linear bandits.

This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them requires a large deal of technical effort and significant modifications to the sta…

Study contextual bandits with stage-wise constraints, proving regret bounds and extending results.

Improved online Q-learning for MDPs with concentration bounds.

Unified high-probability regret bounds for online convex optimisation with randomised gradient estimators.

This paper addresses missing covariates in stochastic linear bandits, providing a high-probability regret bound.

Paper improves worst-case regret bounds for RLSVI in reinforcement learning.

In this paper, the problem of maximizing a black-box function $f:\mathcal{X} \to \mathbb{R}$ is studied in the Bayesian framework with a Gaussian Process (GP) prior. In particular, a new algorithm for this problem is proposed, and high probability bounds on its simple and cumulative regret are established. The query po…

Develops model selection for bandits balancing adversarial and stochastic guarantees.

Unified proof for various bandit algorithms with logarithmic regret.

New algorithm FLUTE achieves uniform-PAC convergence in RL with linear approx.

UCB-V algorithm improves on UCB for MAB problems with variance estimates.

Two non-communicating players minimize regret in a multi-armed bandit game.

Adapts Exp3 to adversarial bandits with delays and data.

This guide simplifies high-probability regret bounds in empirical risk minimization.

Wavelet-based online learning adapts to noisy Besov spaces with high probability.

We provide new lower bounds on the regret that must be suffered by adversarial bandit algorithms. The new results show that recent upper bounds that either (a) hold with high-probability or (b) depend on the total lossof the best arm or (c) depend on the quadratic variation of the losses, are close to tight. Besides th…

This paper analyzes regret bounds for Gaussian process Thompson sampling.

New algorithms reduce regret for online submodular maximization under various conditions.

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high…

New algorithm reduces dynamic regret without prior function change knowledge.

Paper improves regret bounds for Gaussian process upper confidence bound in Bayesian optimization.

Study shows observing order book can significantly improve online market making performance.

Efficient algorithm for zeroth-order bandit convex optimization with bounds on regret.

This paper analyzes data-driven Newsvendor problems and finds a wide range of possible regrets.

We consider the multi-armed bandit setting with a twist. Rather than having just one decision maker deciding which arm to pull in each round, we have $n$ different decision makers (agents). In the simple stochastic setting, we show that a "free-riding" agent observing another "self-reliant" agent can achieve just $O(1)…

Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms called Uniform-PAC, which is a strengthening of the classical Probably Approximatel…

Paper tackles online control of linear systems with unbounded noise.

New strategy achieves optimal regret without communication or collisions in multi-player bandit.

New framework for RL with linear-convex models reduces performance gap.

This paper analyses the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al., 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, (Srinivas et al., 2010) pro…

This paper analyzes the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al, 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, Srinivas et al proved that t…

Algorithm minimizes regret while adhering to unknown safety constraints.

We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves $\mathcal{\tilde{O}}(L|X|\sqrt{|A|T})$ regret with high probability, where $L$ is the horizon, $|X|$ is t…

Algorithm identifies the best arm in linear bandits with high probability.

This work explains why online imitation learning improves faster than theory predicts.

New approach reduces unconstrained linear bandits to simpler optimization problems.

New method for online meta-learning reduces dynamic regret in changing environments.

The paper explores trade-offs between regret and variance in online learning algorithms.

Algorithm minimizes regret in multi-criteria bandits with constraints.

New algorithm for minimizing regret in adversarial dueling bandits.

Study on selecting between base algorithms in stochastic bandit problems.

New method reduces multi-armed bandit regret to near-optimal levels.

GP-PSRL achieves sublinear regret for continuous control with unbounded state space.