Copertina

Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Du, Ally Yalei, Yang, Lin F., Wang, Ruosong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reconciling Model Multiplicity for Downstream Decision Making
di: Du, Ally Yalei, et al.
Pubblicazione: (2024)

The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation
di: Golowich, Noah, et al.
Pubblicazione: (2024)

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
di: Huang, Jiayi, et al.
Pubblicazione: (2023)

Nonasymptotic CLT and Error Bounds for Two-Time-Scale Stochastic Approximation
di: Kong, Seo Taek, et al.
Pubblicazione: (2025)

Second Order Bounds for Contextual Bandits with Function Approximation
di: Pacchiano, Aldo
Pubblicazione: (2024)

Analysis of Off-Policy $n$-Step TD-Learning with Linear Function Approximation
di: Lim, Han-Dong, et al.
Pubblicazione: (2025)

Generative modeling of Sparse Approximate Inverse Preconditioners
di: Li, Mou, et al.
Pubblicazione: (2024)

Universal Approximation Theorem of Deep Q-Networks
di: Qi, Qian
Pubblicazione: (2025)

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage
di: Liu, Haolin, et al.
Pubblicazione: (2026)

List Replicable Reinforcement Learning
di: Zhang, Bohan, et al.
Pubblicazione: (2025)

Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation
di: Gu, Jingwen, et al.
Pubblicazione: (2025)

Fitted Q-Iteration via Max-Plus-Linear Approximation
di: Liu, Y., et al.
Pubblicazione: (2024)

Experiment Planning with Function Approximation
di: Pacchiano, Aldo, et al.
Pubblicazione: (2024)

Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
di: Lee, Sewoong, et al.
Pubblicazione: (2025)

Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation
di: Zhao, Runze, et al.
Pubblicazione: (2025)

Towards Differentially Private Reinforcement Learning with General Function Approximation
di: He, Yi, et al.
Pubblicazione: (2026)

SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
di: Wu, Qitian, et al.
Pubblicazione: (2024)

AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning
di: Pramanik, Subhojeet, et al.
Pubblicazione: (2023)

GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs
di: An, Selim, et al.
Pubblicazione: (2026)

Universal Approximation Theorem for Deep Q-Learning via FBSDE System
di: Qi, Qian
Pubblicazione: (2025)

Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning
di: Rozada, Sergio, et al.
Pubblicazione: (2022)

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
di: Huang, Jiawei, et al.
Pubblicazione: (2023)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
di: Chou, Yuhong, et al.
Pubblicazione: (2024)

Regularized Q-Learning with Linear Function Approximation
di: Xi, Jiachen, et al.
Pubblicazione: (2024)

Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set
di: Liu, Xinyu, et al.
Pubblicazione: (2025)

BELLA: Black box model Explanations by Local Linear Approximations
di: Radulovic, Nedeljko, et al.
Pubblicazione: (2023)

Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation
di: Dong, Yanjie, et al.
Pubblicazione: (2024)

How Sparse Attention Approximates Exact Attention? Your Attention is Naturally $n^C$-Sparse
di: Deng, Yichuan, et al.
Pubblicazione: (2024)

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs
di: Banerjee, Debangshu, et al.
Pubblicazione: (2023)

Learning (Approximately) Equivariant Networks via Constrained Optimization
di: Manolache, Andrei, et al.
Pubblicazione: (2025)

Manifold Approximation leads to Robust Kernel Alignment
di: Islam, Mohammad Tariqul, et al.
Pubblicazione: (2025)

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
di: Cinquin, Tristan, et al.
Pubblicazione: (2024)

Boosting Soft Q-Learning by Bounding
di: Adamczyk, Jacob, et al.
Pubblicazione: (2024)

NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
di: Yu, Jiangyong, et al.
Pubblicazione: (2026)

Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
di: Salaudeen, Olawale, et al.
Pubblicazione: (2025)

The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
di: Yi, Huiyang, et al.
Pubblicazione: (2025)

Enhancing Neural Function Approximation: The XNet Outperforming KAN
di: Li, Xin, et al.
Pubblicazione: (2025)

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
di: Vakili, Sattar, et al.
Pubblicazione: (2024)

Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees
di: Du, Ally Yalei, et al.
Pubblicazione: (2025)

Tight Lower Bounds and Improved Convergence in Performative Prediction
di: Khorsandi, Pedram, et al.
Pubblicazione: (2024)