English
Related papers

Related papers: Bellman-consistent Pessimism for Offline Reinforce…

200 papers

Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in…

Machine Learning · Computer Science 2024-12-30 Huaijie Wang , Shibo Hao , Hanze Dong , Shenao Zhang , Yilin Bao , Ziran Yang , Yi Wu

This work proposes `PET', a novel pessimistic reward fine-tuning method, to learn a pessimistic reward model robust against reward hacking in offline reinforcement learning from human feedback (RLHF). Traditional reward modeling techniques…

Machine Learning · Computer Science 2025-05-28 Yinglun Xu , Hangoo Kang , Tarun Suresh , Yuxuan Wan , Gagandeep Singh

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

Distributionally robust offline reinforcement learning (RL), which seeks robust policy training against environment perturbation by modeling dynamics uncertainty, calls for function approximations when facing large state-action spaces.…

Machine Learning · Computer Science 2025-11-03 Zhishuai Liu , Pan Xu

Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods either suffer from high…

Machine Learning · Computer Science 2021-06-09 Samuele Tosatto , João Carvalho , Jan Peters

We study reinforcement learning with linear function approximation and adversarially changing cost functions, a setup that has mostly been considered under simplifying assumptions such as full information feedback or exploratory…

Machine Learning · Computer Science 2023-01-31 Uri Sherman , Tomer Koren , Yishay Mansour

We propose A-Crab (Actor-Critic Regularized by Average Bellman error), a new practical algorithm for offline reinforcement learning (RL) in complex environments with insufficient data coverage. Our algorithm combines the marginalized…

Machine Learning · Computer Science 2023-10-10 Hanlin Zhu , Paria Rashidinejad , Jiantao Jiao

Improvement guarantees for semi-supervised classifiers can currently only be given under restrictive conditions on the data. We propose a general way to perform semi-supervised parameter estimation for likelihood-based classifiers for…

Machine Learning · Statistics 2015-05-12 Marco Loog

We consider the offline reinforcement learning problem, where the aim is to learn a decision making policy from logged data. Offline RL -- particularly when coupled with (value) function approximation to allow for generalization in large or…

Machine Learning · Computer Science 2022-08-31 Dylan J. Foster , Akshay Krishnamurthy , David Simchi-Levi , Yunzong Xu

While Distributional Reinforcement Learning (DRL) methods have demonstrated strong performance in online settings, its success in offline scenarios remains limited. We hypothesize that a key limitation of existing offline DRL methods lies…

Machine Learning · Computer Science 2026-01-06 Ryo Iwaki , Takayuki Osogami

Double Q-learning is a classical method for reducing overestimation bias, which is caused by taking maximum estimated values in the Bellman operation. Its variants in the deep Q-learning paradigm have shown great promise in producing…

Machine Learning · Computer Science 2022-01-17 Zhizhou Ren , Guangxiang Zhu , Hao Hu , Beining Han , Jianglun Chen , Chongjie Zhang

We study computationally and statistically efficient Reinforcement Learning algorithms for the linear Bellman Complete setting. This setting uses linear function approximation to capture value functions and unifies existing models like…

Machine Learning · Computer Science 2025-03-04 Runzhe Wu , Ayush Sekhari , Akshay Krishnamurthy , Wen Sun

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii)…

Machine Learning · Computer Science 2023-03-21 Siyu Chen , Yitan Wang , Zhaoran Wang , Zhuoran Yang

Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and…

Machine Learning · Computer Science 2023-04-19 Andrew Patterson , Victor Liao , Martha White

We consider the problem of sequential decision making under uncertainty in which the loss caused by a decision depends on the following binary observation. In competitive on-line learning, the goal is to design decision algorithms that are…

Machine Learning · Computer Science 2007-05-23 Vladimir Vovk

Offline reinforcement learning (RL), which refers to decision-making from a previously-collected dataset of interactions, has received significant attention over the past years. Much effort has focused on improving offline RL practicality…

Machine Learning · Computer Science 2022-11-03 Paria Rashidinejad , Hanlin Zhu , Kunhe Yang , Stuart Russell , Jiantao Jiao

Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practical approach to offline RL with large language models…

We present an actor-critic-type reinforcement learning algorithm for solving the problem of hedging a portfolio of financial instruments such as securities and over-the-counter derivatives using purely historic data. The key characteristics…

Computational Finance · Quantitative Finance 2024-06-26 Hans Buehler , Phillip Murray , Ben Wood

We study offline dynamic pricing when historical data provide incomplete coverage of the price space such that some candidate prices, including the optimal one, may be entirely unobserved. This setting is common in practice and is…

Machine Learning · Statistics 2026-05-25 Zeyu Bian , Lan Wang , Zhengling Qi