Cover Image

On the Limited Representational Power of Value Functions and its Links to Statistical (In)Efficiency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheikhi, David, Russo, Daniel
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Statistical Benefits of Temporal Difference Learning
by: Cheikhi, David, et al.
Published: (2023)

Worst-Case Regret Bounds for Exploration via Randomized Value Functions
by: Russo, Daniel
Published: (2019)

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

First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
by: Liu, Ziqi, et al.
Published: (2026)

Stable Offline Value Function Learning with Bisimulation-based Representations
by: Pavse, Brahma S., et al.
Published: (2024)

Reinforcement Learning for Graph Coloring: Understanding the Power and Limits of Non-Label Invariant Representations
by: Cummins, Chase, et al.
Published: (2024)

On The Statistical Limits of Self-Improving Agents
by: Wang, Charles L., et al.
Published: (2025)

What Limits Agentic Systems Efficiency?
by: Bian, Song, et al.
Published: (2025)

On the Theoretical Limitations of Embedding-based Link Prediction
by: Badreddine, Samy, et al.
Published: (2025)

Representation Learning of Lab Values via Masked AutoEncoders
by: Restrepo, David, et al.
Published: (2025)

Efficiency for Free: Ideal Data Are Transportable Representations
by: Sun, Peng, et al.
Published: (2024)

Universal Value-Function Uncertainties
by: Zanger, Moritz A., et al.
Published: (2025)

Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
by: Russo, Daniel
Published: (2026)

Quasimetric Value Functions with Dense Rewards
by: Valieva, Khadichabonu, et al.
Published: (2024)

Inductive Entity Representations from Text via Link Prediction
by: Daza, Daniel, et al.
Published: (2020)

Encoding Temporal Statistical-space Priors via Augmented Representation
by: Choi, Insu, et al.
Published: (2024)

Bridging Theory and Practice in Link Representation with Graph Neural Networks
by: Lachi, Veronica, et al.
Published: (2025)

Learning Human-like Representations to Enable Learning Human Values
by: Wynn, Andrea, et al.
Published: (2023)

Inferring Transition Dynamics from Value Functions
by: Adamczyk, Jacob
Published: (2025)

Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation
by: Peri, Samuele, et al.
Published: (2024)

On The Statistical Representation Properties Of The Perturb-Softmax And The Perturb-Argmax Probability Distributions
by: Indelman, Hedda Cohen, et al.
Published: (2024)

Learning-Based Link Anomaly Detection in Continuous-Time Dynamic Graphs
by: Poštuvan, Tim, et al.
Published: (2024)

Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
by: Auddy, Arnab, et al.
Published: (2026)

Massively Scaling Explicit Policy-conditioned Value Functions
by: Bohlinger, Nico, et al.
Published: (2025)

Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
by: Acharjee, Jashaswimalya, et al.
Published: (2026)

Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiography
by: Maghsoodi, Nooshin, et al.
Published: (2025)

M$^3$-Impute: Mask-guided Representation Learning for Missing Value Imputation
by: Yu, Zhongyi, et al.
Published: (2024)

FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning
by: Li, Jiaoyang, et al.
Published: (2025)

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
by: Nguyen, Tu, et al.
Published: (2026)

Adaptive Exploration for Data-Efficient General Value Function Evaluations
by: Jain, Arushi, et al.
Published: (2024)

Tensor Low-rank Approximation of Finite-horizon Value Functions
by: Rozada, Sergio, et al.
Published: (2024)

VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning
by: Chen, Xuyang, et al.
Published: (2025)

The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
by: Cunnington, Daniel, et al.
Published: (2024)

Revisiting Training Scale: An Empirical Study of Token Count, Power Consumption, and Parameter Efficiency
by: Dwyer, Joe
Published: (2026)

Deep Reinforcement Learning for Inventory Networks: Toward Reliable Policy Optimization
by: Alvo, Matias, et al.
Published: (2023)

GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values
by: Ke, Songyu, et al.
Published: (2025)

Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
by: Park, Sangwoo, et al.
Published: (2025)

Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?
by: Tarasov, Denis, et al.
Published: (2024)

Bayesian Optimization for Function-Valued Responses under Min-Max Criteria
by: Ahadi, Pouya, et al.
Published: (2025)

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