On the public citation graph

Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning

0 signed · 68 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.

Claim with ORCID

Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.

See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1002/9781119808602openalex-snapshot

Model‐Based Reinforcement Learning

inferredcites →https://doi.org/10.1007/3-540-44581-1_39openalex-snapshot

Learning Rates for Q-Learning

inferredcites →https://doi.org/10.1007/978-3-642-24412-4openalex-snapshot

Algorithmic learning theory : 22nd International Conference, ALT 2011, Espoo, Finland, October 5-7, 2011 : proceedings

inferredcites →https://doi.org/10.1007/bf00993306openalex-snapshot

Asynchronous stochastic approximation and Q-learning

inferredcites →https://doi.org/10.1007/s10994-013-5368-1openalex-snapshot

Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model

inferredcites →https://doi.org/10.1007/s10998-010-3055-6openalex-snapshot

UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem

inferredcites →https://doi.org/10.1016/0196-8858(85)90002-8openalex-snapshot

Asymptotically efficient adaptive allocation rules

inferredcites →https://doi.org/10.1016/j.sysconle.2012.08.014openalex-snapshot

Error bounds for constant step-size -learning

inferredcites →https://doi.org/10.1016/s0925-2312(97)90018-7openalex-snapshot

Advances in neural information processing systems 7

inferredcites →https://doi.org/10.1017/9781108571401openalex-snapshot

Bandit Algorithms

inferredcites →https://doi.org/10.1023/a:1022689125041openalex-snapshot

Asynchronous Stochastic Approximation and Q-Learning

inferredcites →https://doi.org/10.1090/gsm/132openalex-snapshot

Topics in Random Matrix Theory

inferredcites →https://doi.org/10.1109/jproc.2020.3028013openalex-snapshot

Variance-Reduced Methods for Machine Learning

inferredcites →https://doi.org/10.1137/1.9781611975031openalex-snapshot

Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms

inferredcites →https://doi.org/10.1137/1.9781611975031.50openalex-snapshot

Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes

inferredcites →https://doi.org/10.1137/20m1331524openalex-snapshot

Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis

inferredcites →https://doi.org/10.1137/s0097539701398375openalex-snapshot

The Nonstochastic Multiarmed Bandit Problem

inferredcites →https://doi.org/10.1145/1143844.1143955openalex-snapshot

PAC model-free reinforcement learning

inferredcites →https://doi.org/10.1162/neco.1994.6.6.1185openalex-snapshot

On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

inferredcites →https://doi.org/10.1214/aoms/1177729586openalex-snapshot

A Stochastic Approximation Method

inferredcites →https://doi.org/10.1214/aop/1176996452openalex-snapshot

On Tail Probabilities for Martingales

inferredcites →https://doi.org/10.1214/ecp.v16-1624openalex-snapshot

Freedman's inequality for matrix martingales

inferredcites →https://doi.org/10.1287/opre.2023.2450openalex-snapshot

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

inferredcites →https://doi.org/10.1287/opre.2023.2451openalex-snapshot

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

inferredcites →https://doi.org/10.17863/cam.132164openalex-snapshot

Learning from Delayed Rewards

inferredcites →https://doi.org/10.2307/2291177openalex-snapshot

Markov Decision Processes: Discrete Stochastic Dynamic Programming.

inferredcites →https://doi.org/10.48550/arxiv.1205.2661openalex-snapshot

REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs

inferredcites →https://doi.org/10.48550/arxiv.1608.02732openalex-snapshot

On Lower Bounds for Regret in Reinforcement Learning

inferredcites →https://doi.org/10.48550/arxiv.1702.07944openalex-snapshot

Stochastic Variance Reduction Methods for Policy Evaluation

inferredcites →https://doi.org/10.48550/arxiv.1703.07710openalex-snapshot

Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

inferredcites →https://doi.org/10.48550/arxiv.1901.00137openalex-snapshot

A Theoretical Analysis of Deep Q-Learning

inferredcites →https://doi.org/10.48550/arxiv.1901.09311openalex-snapshot

Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP

inferredcites →https://doi.org/10.48550/arxiv.1905.06265openalex-snapshot

Stochastic approximation with cone-contractive operators: Sharp $\ell_\infty$-bounds for $Q$-learning

inferredcites →https://doi.org/10.48550/arxiv.1905.12849openalex-snapshot

Provably Efficient Q-Learning with Low Switching Cost

inferredcites →https://doi.org/10.48550/arxiv.1906.03804openalex-snapshot

Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal

inferredcites →https://doi.org/10.48550/arxiv.1906.04697openalex-snapshot

Variance-reduced $Q$-learning is minimax optimal

inferredcites →https://doi.org/10.48550/arxiv.1906.06321openalex-snapshot

Provably Efficient $Q$-learning with Function Approximation via Distribution Shift Error Checking Oracle

inferredcites →https://doi.org/10.48550/arxiv.1907.05388openalex-snapshot

Provably Efficient Reinforcement Learning with Linear Function Approximation

inferredcites →https://doi.org/10.48550/arxiv.2001.01898openalex-snapshot

Reanalysis of Variance Reduced Temporal Difference Learning

inferredcites →https://doi.org/10.48550/arxiv.2002.00260openalex-snapshot

Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning

inferredcites →https://doi.org/10.48550/arxiv.2002.00874openalex-snapshot

Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes

inferredcites →https://doi.org/10.48550/arxiv.2004.10019openalex-snapshot

Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition

inferredcites →https://doi.org/10.48550/arxiv.2006.03864openalex-snapshot

Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity

inferredcites →https://doi.org/10.48550/arxiv.2006.04354openalex-snapshot

A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret

inferredcites →https://doi.org/10.48550/arxiv.2006.09118openalex-snapshot

$Q$-learning with Logarithmic Regret

inferredcites →https://doi.org/10.48550/arxiv.2007.15418openalex-snapshot

Momentum Q-learning with Finite-Sample Convergence Guarantee

inferredcites →https://doi.org/10.48550/arxiv.2009.13503openalex-snapshot

Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon

inferredcites →https://doi.org/10.48550/arxiv.2009.14257openalex-snapshot

Finite-Time Analysis for Double Q-learning

inferredcites →https://doi.org/10.48550/arxiv.2010.00587openalex-snapshot

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

inferredcites →https://doi.org/10.48550/arxiv.2102.01567openalex-snapshot

A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants

inferredcites →https://doi.org/10.48550/arxiv.2102.01748openalex-snapshot

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

inferredcites →https://doi.org/10.48550/arxiv.2105.08024openalex-snapshot

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

inferredcites →https://doi.org/10.48550/arxiv.2105.14016openalex-snapshot

Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model

inferredcites →https://doi.org/10.48550/arxiv.2208.05767openalex-snapshot

Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity

inferredcites →https://doi.org/10.52202/068431-1117openalex-snapshot

Minimax-Optimal Multi-Agent RL in Markov Games with a Generative Model

inferredcites →https://doi.org/10.5555/1005332.1005333openalex-snapshot

Learning Rates for Q-learning

inferredcites →https://doi.org/10.5555/1756006.1859902openalex-snapshot

Near-optimal Regret Bounds for Reinforcement Learning

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.2139/ssrn.5048272openalex-extracted

Mean-Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study

inferred← citeshttps://doi.org/10.1016/j.apenergy.2023.121785openalex-snapshot

CIRLEM: a synergic integration of Collective Intelligence and Reinforcement learning in Energy Management for enhanced climate resilience and lightweight computation

inferred← citeshttps://doi.org/10.1051/jnwpu/20264420380openalex-snapshot

Hierarchical planning and control for multi-UAV cooperative encirclement in complex environments

inferred← citeshttps://doi.org/10.1109/cac67268.2025.11486883openalex-snapshot

Hierarchical Multi-Agent Affine Formation Control with DRL-Based Obstacle Avoidance and Nonlinear Path Planning

inferred← citeshttps://doi.org/10.1109/icra48891.2023.10160585openalex-snapshot

Learning State Conditioned Linear Mappings for Low-Dimensional Control of Robotic Manipulators

inferred← citeshttps://doi.org/10.1109/tit.2021.3120096openalex-snapshot

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

inferred← citeshttps://doi.org/10.1109/tit.2024.3522347openalex-snapshot

Minimax Optimal Q Learning With Nearest Neighbors

inferred← citeshttps://doi.org/10.1214/23-aos2342openalex-snapshot

Settling the sample complexity of model-based offline reinforcement learning

inferred← citeshttps://doi.org/10.1287/opre.2023.2450openalex-snapshot

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

inferred← citeshttps://doi.org/10.1609/aaai.v37i6.25872openalex-snapshot

Offline Quantum Reinforcement Learning in a Conservative Manner

inferred← citeshttps://doi.org/10.1609/aaai.v38i10.28953openalex-snapshot

Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge

Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.