Image de couverture de livre

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Kaiwen, Oertell, Owen, Agarwal, Alekh, Kallus, Nathan, Sun, Wen
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Central Role of the Loss Function in Reinforcement Learning
par: Wang, Kaiwen, et autres
Publié: (2024)

A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents
par: Wang, Kaiwen, et autres
Publié: (2024)

Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling
par: Agarwal, Alekh, et autres
Publié: (2022)

Convergence Of Consistency Model With Multistep Sampling Under General Data Assumptions
par: Chen, Yiding, et autres
Publié: (2025)

Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
par: Bennett, Andrew, et autres
Publié: (2024)

Robust and Agnostic Learning of Conditional Distributional Treatment Effects
par: Kallus, Nathan, et autres
Publié: (2022)

Bellman Calibration for $V$-Learning in Offline Reinforcement Learning
par: van der Laan, Lars, et autres
Publié: (2025)

LLMs Can Learn to Reason Via Off-Policy RL
par: Ritter, Daniel, et autres
Publié: (2026)

Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning
par: Ayoub, Alex, et autres
Publié: (2024)

A Minimaximalist Approach to Reinforcement Learning from Human Feedback
par: Swamy, Gokul, et autres
Publié: (2024)

Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Model
par: Kallus, Nathan
Publié: (2025)

Efficient Controllable Diffusion via Optimal Classifier Guidance
par: Oertell, Owen, et autres
Publié: (2025)

Variation Due to Regularization Tractably Recovers Bayesian Deep Learning
par: McInerney, James, et autres
Publié: (2024)

Efficient Inference for Inverse Reinforcement Learning and Dynamic Discrete Choice Models
par: van der Laan, Lars, et autres
Publié: (2025)

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds
par: Wang, Zhiyong, et autres
Publié: (2024)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
par: Zhou, Jin Peng, et autres
Publié: (2025)

Inverse Reinforcement Learning with Just Classification and a Few Regressions
par: van der Laan, Lars, et autres
Publié: (2025)

Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization
par: Marinov, Teodor V., et autres
Publié: (2024)

Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
par: Oprescu, Miruna, et autres
Publié: (2024)

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data
par: Kallus, Nathan, et autres
Publié: (2020)

RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
par: Oertell, Owen, et autres
Publié: (2024)

Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach
par: Hao, Guang-Yuan, et autres
Publié: (2026)

Value-Guided Search for Efficient Chain-of-Thought Reasoning
par: Wang, Kaiwen, et autres
Publié: (2025)

Preserving Expert-Level Privacy in Offline Reinforcement Learning
par: Sharma, Navodita, et autres
Publié: (2024)

DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
par: Zhao, Hanyang, et autres
Publié: (2025)

Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference
par: van der Laan, Lars, et autres
Publié: (2025)

Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
par: Ye, Chenlu, et autres
Publié: (2025)

Design Considerations in Offline Preference-based RL
par: Agarwal, Alekh, et autres
Publié: (2025)

Demistifying Inference after Adaptive Experiments
par: Bibaut, Aurélien, et autres
Publié: (2024)

REBEL: Reinforcement Learning via Regressing Relative Rewards
par: Gao, Zhaolin, et autres
Publié: (2024)

Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
par: Sun, Ke, et autres
Publié: (2021)

Multi-Armed Bandits with Interference
par: Jia, Su, et autres
Publié: (2024)

Stationary Reweighting Yields Local Convergence of Soft Fitted Q-Iteration
par: van der Laan, Lars, et autres
Publié: (2025)

Fitted $Q$ Evaluation Without Bellman Completeness via Stationary Weighting
par: van der Laan, Lars, et autres
Publié: (2025)

TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
par: Yoo, Kiwoong, et autres
Publié: (2024)

Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models
par: Belenki, Lior, et autres
Publié: (2025)

Mitigating Preference Hacking in Policy Optimization with Pessimism
par: Gupta, Dhawal, et autres
Publié: (2025)

Exploration in the Limit
par: Cho, Brian M., et autres
Publié: (2025)

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams
par: Cho, Brian, et autres
Publié: (2024)

Entropy After </Think> for reasoning model early exiting
par: Wang, Xi, et autres
Publié: (2025)