Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

306089119 · May 202619922001200920172026
48 results for regret horizon

UCRL-WVTR tackles long-term reinforcement learning with general approximations, achieving horizon-free and instance-dependent regret bounds.

problem Long-term reinforcement learning with general function approximations.
method UCRL-WVTR proposes a novel algorithm, UCRL-WVTR, with weighted value-targeted regression and a high-order moment estimator.
result Achieves horizon-free and instance-dependent regret bounds matching minimax lower bounds up to logarithmic factors.

New algorithm achieves asymptotically optimal regret without horizon dependence.

problem Horizon-free regret minimization for reinforcement learning.
method Proposes a new algorithm and proves a regret upper bound.
result Regret upper bound of \(\tilde O(\sqrt{SAK} + S^8A^3)\) with failure probability \(\delta\).

This paper improves Thompson Sampling for complex decision-making problems.

problem Learning in infinite-horizon discounted decision processes with unknown parameters.
method Developed a general canonical probability space and new metrics for analyzing adaptive learning algorithms.
result Thompson Sampling achieves complete learning in complex decision-making problems.

New algorithms minimize regret in SSP with optimal sparse updates.

problem Minimizing regret in Stochastic Shortest Path models.
method Implicit finite-horizon approximation for analysis, model-free and model-based algorithms developed.
result Minimax optimal regret for both model-free and model-based algorithms.

Paper proposes an efficient online learning method using an offline dataset for infinite horizon MDPs.

problem Efficient online reinforcement learning in infinite horizon MDPs with an unknown expert policy.
method Bayesian approach to model the expert's policy and minimize cumulative regret.
result Upper bound on regret of ildeO(T) ilde{O}(\sqrt{T}) for the Informed PSRL algorithm.

Significant improvements in regret analysis for adaptive online learning problems.

problem Exploiting low variance in online learning problems without known variances.
method Novel peeling-based regret analysis leveraging elliptical potential `count` lemma.
result Significant improvements in regret bounds for linear bandits and linear mixture MDPs.

A new model-free algorithm achieves near-optimal regret for infinite-horizon MDPs.

problem Model-free reinforcement learning for infinite-horizon average-reward MDPs.
method Exploration Enhanced Q-learning (EE-QL) for weakly communicating MDPs.
result Achieves O(T)O(\sqrt{T}) regret bound for general weakly communicating MDPs.

Logarithmic regret achieved in continuous-time linear-quadratic reinforcement learning.

problem Optimizing control actions in unknown continuous-time systems over a finite time horizon.
method Least-squares algorithm based on continuous-time observations and controls, with perturbation analysis and parameter estimation error analysis.
result Logarithmic regret bound of order O((lnM)(lnlnM))O((\ln M)(\ln\ln M)).

We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret O~(H5MK+εHK)\tilde{\mathcal{O}}(\sqrt{H^5 M K} + εHK), where HH is the horizon, MM is the number of aggregate states, KK is the number of episodes, and εε is …

2019-12-13abs ↗pdf ↗

New algorithms for learning MDPs with linear approximations in infinite-horizon settings.

problem Learning infinite-horizon average-reward MDPs with linear function approximation.
method Optimism principle, adversarial linear bandits, Natural Policy Gradient.
result Efficient algorithms with optimal or near-optimal regret bounds.

New algorithms learn MDPs with better regret bounds using generative sampling.

problem Learning MDPs with optimal policies under uncertainty.
method Hybrid exploration-generative RL model, classical and quantum algorithms.
result Quantum algorithms achieve polylogT\operatorname{poly}\log{T} regret for infinite-horizon MDPs.

Logarithmic regret for continuous-time reinforcement learning.

problem Continuous-time Markov decision processes with unknown transition probabilities and holding times.
method Upper confidence reinforcement learning, mean holding time estimation, stochastic comparison of point processes.
result Logarithmic regret bound achieved in finite time.

New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.

problem Challenges in online reinforcement learning for non-episodic, finite-horizon MDPs.
method Introduces a K-step lookahead Q-function with a time-varying threshold for selecting actions.
result Achieves minimax optimal constant regret for K=1 and O(max((K1),CK1)SATlog(T))\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)}) regret for K ≥ 2.

New algorithms reduce contextual bandits' regret without knowing reward noise variances.

problem Reducing regret in contextual bandits with unknown reward noise variances.
method Developed new algorithms based on the optimism principle.
result Regret scales as the square root of the sum of measurement variances, not the time horizon.

UCRL2-VTR achieves nearly optimal regret for learning MDPs with linear function approximation.

problem Learning infinite-horizon average-reward MDPs with linear function approximation.
method UCRL2-VTR algorithm with Bernstein-type bonus.
result Achieves a regret of ildeO(dDT) ilde{O}(d\sqrt{DT}) with matching lower bound.

Kernel-UCBVI algorithm balances exploration and exploitation in metric state-action spaces.

problem Exploration-exploitation dilemma in finite-horizon reinforcement learning with metric state-action spaces.
method Kernel-UCBVI, leveraging smoothness and kernel estimators of rewards and transitions.
result First regret bound for kernel-based RL using smoothing kernels, O(H3K2d/(2d+1))O(H^3 K^{2d/(2d+1)}).

Efficient RL for linear MDPs with unknown transitions.

problem Long planning horizons and unknown state transitions in linear mixture MDPs.
method Horizon-free algorithm using weighted least squares with variance and uncertainty awareness.
result Achieves optimal regret up to logarithmic factors.

Unified online tensor learning algorithm reduces computational and memory costs.

problem Efficiently learning from large tensors with minimal data storage and timely predictions.
method oRGrad algorithm for online tensor learning.
result oRGrad achieves optimal O(T1/2)O(T^{1/2}) regret and O(logT)O(\log T) adaptive regret.

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

problem Minimizing regret in reinforcement learning with randomized value functions.
method Introduces a clipping variant of Thompson Sampling for RLSVI.
result Achieves a ildeO(H2SAT) ilde{\mathrm{O}}(H^2S\sqrt{AT}) worst-case regret bound.

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in hindsight) and comes with the strongest finite-time regret guarantees for a hori…

2016-03-29abs ↗pdf ↗

Study optimal policy regret in partially observable Markov games with adaptive opponents.

problem Optimal sequential decision-making in partially observable environments against strategic, adaptive opponents.
method An epoch-based optimistic maximum-likelihood algorithm that selects one policy per epoch using confidence sets built cumulatively from past data.
result Achieves ildeO(T) ilde{O}(\sqrt{T}) policy regret for fixed problem parameters, with explicit dependence on horizon, adversary memory, confidence radius, and aggregate Eluder dimension.

We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This includes several well studied and fundamental frameworks such as the Kalman filter and the linear quadratic regulator. State of the art met…

2019-09-11abs ↗pdf ↗

Algorithm minimizes regret in multi-criteria bandits with constraints.

problem Optimize primary attribute while respecting secondary constraints.
method Con-LCB algorithm that guarantees logarithmic regret and feasibility identification.
result Logarithmic regret and feasibility identification with high probability.

In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications such as online reco…

2018-10-08abs ↗pdf ↗

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 O~(LXAT)\mathcal{\tilde{O}}(L|X|\sqrt{|A|T}) regret with high probability, where LL is the horizon, X|X| is t…

2019-12-03abs ↗pdf ↗

We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfeasible and some form of function approximation is mandatory. In this paper, we introduce an optimistically-initialized variant of the popula…

2019-11-01abs ↗pdf ↗

New algorithm reduces reinforcement learning regret to sqrt(T) without strong dynamics assumptions.

problem Infinite-horizon average-reward reinforcement learning with linear MDPs.
method Approximate by discounted-reward MDPs and apply optimistic value iteration.
result Achieves O(sqrt(T)) regret with polynomial complexity.

Algorithm reduces long-term policy regret in ML decision-making.

problem Capturing long-term impacts of ML decisions in communities.
method Modeling communities as arms in a multi-armed bandit problem, defining policy regret as a stronger metric than external regret.
result Algorithm achieves provably sub-linear policy regret for long time horizons.

Algorithm reduces regret in partially observable systems by learning dynamics and using optimistic control.

problem Minimizing regret in partially observable linear quadratic control systems with unknown dynamics.
method ExpCommit algorithm that learns model parameters and uses optimism in uncertainty.
result End-to-end sublinear regret upper bound of O~(T2/3)\tilde{\mathcal{O}}(T^{2/3}) for ExpCommit.

Optimal switching regret for all segmentations in online convex optimisation.

problem Non-stationary online convex optimisation problems.
method Developed an efficient algorithm to achieve optimal switching regret on every possible segmentation.
result Achieved asymptotically optimal switching regret on every possible segmentation simultaneously.