"function approximation" Papers

19 papers found

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

Hyungkyu Kang, Min-hwan Oh

ICLR 2025posterarXiv:2503.05306
3
citations

Attention Mechanism, Max-Affine Partition, and Universal Approximation

Hude Liu, Jerry Yao-Chieh Hu, Zhao Song et al.

NEURIPS 2025posterarXiv:2504.19901
6
citations

Finite-Time Bounds for Average-Reward Fitted Q-Iteration

Jongmin Lee, Ernest Ryu

NEURIPS 2025posterarXiv:2510.17391

From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs

Xin Li, Xiaotao Zheng, Zhihong Xia

NEURIPS 2025poster

Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory

Alexander Levine, Peter Stone, Amy Zhang

ICLR 2025posterarXiv:2410.03016
1
citations

Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach

Swetha Ganesh, Vaneet Aggarwal

NEURIPS 2025posterarXiv:2505.19986
2
citations

Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback

Orin Levy, Liad Erez, Alon Peled-Cohen et al.

NEURIPS 2025spotlightarXiv:2510.09127

Revisiting a Design Choice in Gradient Temporal Difference Learning

Xiaochi Qian, Shangtong Zhang

ICLR 2025oralarXiv:2308.01170
6
citations

Reward-Aware Proto-Representations in Reinforcement Learning

Hon Tik Tse, Siddarth Chandrasekar, Marlos C. Machado

NEURIPS 2025oralarXiv:2505.16217
1
citations

Second Order Bounds for Contextual Bandits with Function Approximation

Aldo Pacchiano

ICLR 2025posterarXiv:2409.16197
7
citations

Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation

Chenyu Zhang, Xu Chen, Xuan Di

ICLR 2025posterarXiv:2408.08192
7
citations

Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding

Qian Ma, Ruoxiang Xu, Yongqiang Cai

NEURIPS 2025posterarXiv:2511.06376

ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints

Akhil Agnihotri, Rahul Jain, Haipeng Luo

ICML 2024posterarXiv:2302.00808

Characterizing ResNet's Universal Approximation Capability

Chenghao Liu, Enming Liang, Minghua Chen

ICML 2024poster

Imitation Learning in Discounted Linear MDPs without exploration assumptions

Luca Viano, EFSTRATIOS PANTELEIMON SKOULAKIS, Volkan Cevher

ICML 2024posterarXiv:2405.02181

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL

Jiawei Huang, Niao He, Andreas Krause

ICML 2024posterarXiv:2402.05724

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback

Asaf Cassel, Haipeng Luo, Aviv Rosenberg et al.

ICML 2024posterarXiv:2405.07637

On The Statistical Complexity of Offline Decision-Making

Thanh Nguyen-Tang, Raman Arora

ICML 2024posterarXiv:2501.06339

Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping Compositions

Yongqiang Cai

ICML 2024spotlightarXiv:2305.12205