arXiv research

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

New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.

New algorithm reduces reinforcement learning regret for linear MDPs with unknown transitions.

New algorithms achieve logarithmic regret in learning linear quadratic control systems.

New RL algorithm tackles adversarial RMAB with unknown transitions and bandit feedback.

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

We study learning latent models with multi-instance weak supervision.

New method for state inference in state-space models with unknown dynamics.

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…

New algorithm reduces suboptimality in imitation learning to nearly optimal levels.

Efficient RL for linear MDPs with unknown transitions.

The problem of estimating an unknown discrete distribution from its samples is a fundamental tenet of statistical learning. Over the past decade, it attracted significant research effort and has been solved for a variety of divergence measures. Surprisingly, an equally important problem, estimating an unknown Markov ch…

We tackle tensor denoising with unknown permutations, achieving optimal recovery with polynomial estimators.

Machine learning predicts synchronization transitions in unknown systems.

The paper tackles joint learning of linear systems, improving accuracy with pooled data.

The paper tackles resource allocation for arms with unknown and random rewards, achieving optimal regret bounds.

Method determines credit transition matrix from cumulative default probabilities.

Reinforcement learning with trajectory feedback instead of state-action rewards.

We consider the problem of estimating the transition rate matrix of a continuous-time Markov chain from a finite-duration realisation of this process. We approach this problem in an imprecise probabilistic framework, using a set of prior distributions on the unknown transition rate matrix. The resulting estimator is a …

Algorithm POLO learns low-rank MDPs with adversarial changes in full-info feedback.

Optimal sequential testing for Markovian data with lower and upper bounds.

This research improves dynamical systems understanding by identifying latent states and their nonlinear transitions.

New algorithms handle phase retrieval with rank d measurements, revealing phase transitions.

New algorithm minimizes regret in unknown LQ control systems.

This paper presents several models addressing optimal portfolio choice, optimal portfolio liquidation, and optimal portfolio transition issues, in which the expected returns of risky assets are unknown. Our approach is based on a coupling between Bayesian learning and dynamic programming techniques that leads to partia…

We tackle the problem of acting in an unknown finite and discrete Markov Decision Process (MDP) for which the expected shortest path from any state to any other state is bounded by a finite number $D$. An MDP consists of $S$ states and $A$ possible actions per state. Upon choosing an action $a_t$ at state $s_t$, one re…

Study best arm identification in restless bandits with unknown TPMs.

Study learns linear system dynamics from noisy bilinear data.

Deep reinforcement learning finds optimal learning policies for adaptive systems.

Study on estimating signals from shifted and noisy copies in high dimensions, revealing a phase transition.

Model-based Bayesian Reinforcement Learning (BRL) allows a found formalization of the problem of acting optimally while facing an unknown environment, i.e., avoiding the exploration-exploitation dilemma. However, algorithms explicitly addressing BRL suffer from such a combinatorial explosion that a large body of work r…

New algorithm optimizes resource allocation in non-stationary networks.

PQR estimates reward functions from actions and states without assuming state-only rewards.

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the …

This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: -We establish new minimax-rates for active learning under common \textit{noise conditions}. These rates display interesting transitions -- due to the inte…

Efficient RL algorithm for multinomial logistic MDPs with provable guarantees.

Gradient descent solves rank-one matrix estimation problem with detailed time evolution analysis.

The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, c…

Estimates stationary distribution from batch transitions without access to the underlying process.

The paper explores how low-degree polynomials can detect shuffled linear regression models.

SCPO learns robust policies without modeling disturbance, improving real-world task performance.

Improved KSD test for better detection of differences in distributions.

It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth labels by an unknown noise transition matrix. Thus, by estimating this matrix, classifiers can escape from overfitting those noisy labels. …

New method detects changes in high-dimensional Markov processes without explicit likelihood evaluation.

Tyler's M-estimator's phase transition at DS-SNR = 1 is resolved.

Solves inventory control with unknown demand trend using singular control.

Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for settings in which the reward function and the constraints, described by cost functi…

Unified framework for learning with indirect supervision signals.