Image de couverture de livre

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Foster, Dylan J., Mhammedi, Zakaria, Rohatgi, Dhruv
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Statistics Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
par: Golowich, Noah, et autres
Publié: (2026)

The Power of Resets in Online Reinforcement Learning
par: Mhammedi, Zakaria, et autres
Publié: (2024)

Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions
par: Mhammedi, Zakaria
Publié: (2024)

Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
par: Rohatgi, Dhruv, et autres
Publié: (2025)

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback
par: Li, Gen, et autres
Publié: (2025)

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
par: Foster, Dylan J., et autres
Publié: (2024)

The Coverage Principle: How Pre-Training Enables Post-Training
par: Chen, Fan, et autres
Publié: (2025)

Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity
par: Amortila, Philip, et autres
Publié: (2024)

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
par: Lin, Licong, et autres
Publié: (2023)

Self-Improvement in Language Models: The Sharpening Mechanism
par: Huang, Audrey, et autres
Publié: (2024)

Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods
par: Hu, Xinyang, et autres
Publié: (2024)

Statistical and Algorithmic Foundations of Reinforcement Learning
par: Chi, Yuejie, et autres
Publié: (2025)

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models
par: Rajendran, Goutham, et autres
Publié: (2024)

Provable Reward-Agnostic Preference-Based Reinforcement Learning
par: Zhan, Wenhao, et autres
Publié: (2023)

Efficient Model-Free Exploration in Low-Rank MDPs
par: Mhammedi, Zakaria, et autres
Publié: (2023)

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
par: Chen, Fan, et autres
Publié: (2025)

Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps
par: Kelner, Jonathan, et autres
Publié: (2024)

Cyclic Counterfactuals under Shift-Scale Interventions
par: Saha, Saptarshi, et autres
Publié: (2025)

Foundations of Top-$k$ Decoding For Language Models
par: Noarov, Georgy, et autres
Publié: (2025)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
par: Su, Xun, et autres
Publié: (2025)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
par: Hariri, Mohsen, et autres
Publié: (2025)

A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees
par: Yan, Hedong
Publié: (2025)

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
par: Baharav, Tavor Z., et autres
Publié: (2025)

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
par: Lu, Miao, et autres
Publié: (2022)

Foundations of Structural Causal Models with Latent Selection
par: Chen, Leihao, et autres
Publié: (2024)

FraPPE: Fast and Efficient Preference-based Pure Exploration
par: Das, Udvas, et autres
Publié: (2025)

Counterfactual reasoning: an analysis of in-context emergence
par: Miller, Moritz, et autres
Publié: (2025)

Reasoning with Sampling: Cutting at Decision Points
par: Zhou, Felix, et autres
Publié: (2026)

On the Provable Performance Guarantee of Efficient Reasoning Models
par: Zeng, Hao, et autres
Publié: (2025)

RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
par: Hao, Sai, et autres
Publié: (2026)

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
par: Mei, Song
Publié: (2024)

Diffusion Posterior Sampling is Computationally Intractable
par: Gupta, Shivam, et autres
Publié: (2024)

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
par: Guo, Yang, et autres
Publié: (2025)

Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
par: Li, Gen, et autres
Publié: (2024)

Scaling Laws in Linear Regression: Compute, Parameters, and Data
par: Lin, Licong, et autres
Publié: (2024)

A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models
par: Cai, Yinpeng, et autres
Publié: (2025)

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
par: Chen, Fan, et autres
Publié: (2022)

Efficient Knowledge Distillation via Curriculum Extraction
par: Gupta, Shivam, et autres
Publié: (2025)

A Differential and Pointwise Control Approach to Reinforcement Learning
par: Nguyen, Minh, et autres
Publié: (2024)

How Particle-System Random Batch Methods Enhance Graph Transformer: Memory Efficiency and Parallel Computing Strategy
par: Liu, Hanwen, et autres
Publié: (2025)