Cover Image

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aouali, Imad, Brunel, Victor-Emmanuel, Rohde, David, Korba, Anna
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

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces
by: Aouali, Imad, et al.
Published: (2024)

Diffusion Models Meet Contextual Bandits
by: Aouali, Imad
Published: (2024)

PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
by: Zitouni, Abdelkrim, et al.
Published: (2025)

Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
by: Lin, Hongqiang, et al.
Published: (2026)

Mitigating Preference Hacking in Policy Optimization with Pessimism
by: Gupta, Dhawal, et al.
Published: (2025)

Offline Contextual Bandit with Counterfactual Sample Identification
by: Gilotte, Alexandre, et al.
Published: (2025)

Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation
by: Aouali, Imad, et al.
Published: (2025)

Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
by: Gao, Chen-Xiao, et al.
Published: (2025)

RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
by: Aouali, Imad, et al.
Published: (2026)

Regional Explanations: Bridging Local and Global Variable Importance
by: Amoukou, Salim I., et al.
Published: (2026)

Federated Offline Policy Optimization with Dual Regularization
by: Yue, Sheng, et al.
Published: (2024)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
by: Liu, Tenglong, et al.
Published: (2024)

When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
by: Liu, Vincent, et al.
Published: (2023)

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
by: Lu, Miao, et al.
Published: (2022)

ESPO: Entropy Importance Sampling Policy Optimization
by: Sheng, Yuepeng, et al.
Published: (2025)

GIPO: Gaussian Importance Sampling Policy Optimization
by: Lu, Chengxuan, et al.
Published: (2026)

PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
by: Lee, Jaejun, et al.
Published: (2024)

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
by: Liu, Zongkai, et al.
Published: (2024)

Mutual Information Regularized Offline Reinforcement Learning
by: Ma, Xiao, et al.
Published: (2022)

Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning
by: Humayoo, Mahammad, et al.
Published: (2018)

Beyond Importance Sampling: Rejection-Gated Policy Optimization
by: Sun, Ziwu, et al.
Published: (2026)

The Role of Deep Learning Regularizations on Actors in Offline RL
by: Tarasov, Denis, et al.
Published: (2024)

Entropy-Regularized Adjoint Matching for Offline Reinforcement Learning
by: Ghanem, Abdelghani, et al.
Published: (2026)

Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning
by: Chen, Haohui, et al.
Published: (2025)

Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
by: Hsu, Hsiang, et al.
Published: (2026)

Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
by: Woydt, Tim, et al.
Published: (2026)

Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
by: Sakhi, Otmane, et al.
Published: (2024)

Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds
by: Hennequin, Mehdi, et al.
Published: (2024)

Offline Reinforcement Learning with Generative Trajectory Policies
by: Feng, Xinsong, et al.
Published: (2025)

Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
by: Zhou, Hongyi, et al.
Published: (2025)

Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits
by: Zhao, Qingyue, et al.
Published: (2025)

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
by: Ji, Kaixuan, et al.
Published: (2026)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
by: Tu, Songjun, et al.
Published: (2024)

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
by: Hossain, Elias, et al.
Published: (2026)

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
by: Zhang, Yuheng, et al.
Published: (2026)

Policy-regularized Offline Multi-objective Reinforcement Learning
by: Lin, Qian, et al.
Published: (2024)

Policy-Based Trajectory Clustering in Offline Reinforcement Learning
by: Hu, Hao, et al.
Published: (2025)

Evaluation-Time Policy Switching for Offline Reinforcement Learning
by: Neggatu, Natinael Solomon, et al.
Published: (2025)

Sample Efficient Active Algorithms for Offline Reinforcement Learning
by: Roy, Soumyadeep, et al.
Published: (2026)

Latent Adversarial Regularization for Offline Preference Optimization
by: Jiang, Enyi, et al.
Published: (2026)