arXiv research

A new estimator for evaluating policies in unknown environments.

Study designs logging policies to minimize off-policy evaluation error.

New algorithm learns safe policies in unknown environments.

New RL algorithm reduces policy switching cost to loglog(T) with similar regret.

New algorithm minimizes regret in unknown LQ control systems.

As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the po…

We study the pricing problem faced by a firm that sells a large number of products, described via a wide range of features, to customers that arrive over time. Customers independently make purchasing decisions according to a general choice model that includes products features and customers' characteristics, encoded as…

Algorithm learns interference network and optimizes treatment allocation for unknown network effects.

Paper addresses online alignment of large language models under uncertain preference feedback.

Bayesian regularization improves policy performance in noisy MDPs.

A robust method for off-policy evaluation in contextual bandits.

Extends OPE to evaluate policies using diverse logging data.

We consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarmed bandit model, players can pick among many arms, and each play of an arm generates an i.i.d. rewar…

Ad exchanges use CORP to set reserve prices against strategic buyers.

Safe-M$^3$-UCRL learns safe policies for multi-agent systems with global constraints.

We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs. The features are kno…

New algorithm tackles adversarial RL without horizon constraints.

This paper optimizes off-policy evaluation in reinforcement learning with function approximation.

Develops an anytime-valid framework for optimal policy identification from logged contextual bandit data.

Proposes log density gradient to improve reinforcement learning sample complexity.

Paper tackles policy selection with logged data and limited online interactions.

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a sub-linear, $O(\sqrt{T}\log T)$, regret bound for a variant of Thompson sampling. Our…

Study minimax off-policy evaluation in multi-armed bandits with known and unknown behavior policies.

We consider a firm that sells a large number of products to its customers in an online fashion. Each product is described by a high dimensional feature vector, and the market value of a product is assumed to be linear in the values of its features. Parameters of the valuation model are unknown and can change over time.…

New bounds for learning near-optimal policies in CMDPs with constraints.

New algorithm reduces online learning error for unknown feature distributions.

This work learns exploration policies for unknown distributions using samples and policy gradients.

New algorithm tackles dynamic query routing to multiple embedding models.

Meta-learning control algorithm with finite-time guarantees for unknown systems.

A new method combines online and offline learning to tackle contextual bandits with missing action support.

Paper finds efficient OPE estimator for multiple logging policies with minimum variance.

Study on policy gradient for stochastic bandits using diffusion approximation.

New algorithm achieves data-dependent regret bounds in MDPs with unknown transitions.

When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a colle…

Novel LSE estimator improves off-policy learning and evaluation.

This paper introduces the first asymptotically optimal strategy for a multi armed bandit (MAB) model under side constraints. The side constraints model situations in which bandit activations are limited by the availability of certain resources that are replenished at a constant rate. The main result involves the deriva…

DOLCE improves off-policy evaluation and learning by decomposing effects.

Improved POMDP regret to sqrt(T) with known observation model.

Paper proposes a new DR estimator for adaptive experiments with improved performance.

We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy. Prior work addresses this problem either when only logged data is available, or purely…

New method selects best offline RL policies from logged data.

We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit dependent cost. Successive samples from each population are iid random variables with u…

Greedy policy maximizes information in unknown linear systems.

Study improves unbiased recommender learning by addressing missing-reward bias.

Study online control of unknown time-varying systems with negative and positive results.

ZSPO optimizes RL from unknown link functions using human feedback.

New RL algorithm optimizes policies with bandit feedback, matching previous bounds.

Develops a support-aware framework for reserve-policy selection in advertising markets.