paper-with-me

Papers

Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits

2023-06-13 · Lequn Wang, Akshay Krishnamurthy, Aleksandrs Slivkins

We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions. While pessimistic regularizers are typically used to mitigate distribution shift, prior implementations thereof are either specialized or computationally inefficient. We present the first general oracle-efficient algorithm for pessimistic OPO: it reduces to supervised learning, leading to broad applicability. We obtain statistical guarantees analogous to those for prior pessimistic approaches. We instantiate our approach for both discrete and continuous actions and perform experiments in both settings, showing advantage over unregularized OPO across a wide range of configurations.

📄 PDF Abstract BibTeX arXiv:2306.07923

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

2026-02-27 · Xiang Li, Yuheng Zhang, Nan Jiang arxiv

We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the theoretical foundations of learning a go…

Reinforcement LearningOffline RL

Beyond Pessimism: Offline Learning in KL-regularized Games

2026-04-08 · Yuheng Zhang, Claire Chen, Nan Jiang arxiv

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work relies on pessimistic value estimation to…

Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization

2021-11-27 · ICLR 2022 4 · Thanh Nguyen-Tang, Sunil Gupta, A. Tuan Nguyen, Svetha Venkatesh

Offline policy learning (OPL) leverages existing data collected a priori for policy optimization without any active exploration. Despite the prevalence and recent interest in this problem, its theoretical and algorithmic…

Multi-Armed Bandits

Generalization in offline RL: The structure is more important than the amount of pessimism

2026-07-02 · Max Weltevrede, Matthijs T. J. Spaan, Wendelin Böhmer arxiv

While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization. However, in this paper we demonstrate …

Reinforcement LearningData AugmentationOffline RL

Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

2023-05-16 · NeurIPS 2023 11

In this paper, we study distributionally robust offline reinforcement learning (robust offline RL), which seeks to find an optimal policy purely from an offline dataset that can perform well in perturbed environments. In…

Offline RL