English
Related papers

Related papers: Bellman-consistent Pessimism for Offline Reinforce…

200 papers

This paper aims at theoretically and empirically comparing two standard optimization criteria for Reinforcement Learning: i) maximization of the mean value and ii) minimization of the Bellman residual. For that purpose, we place ourselves…

Machine Learning · Computer Science 2017-12-13 Matthieu Geist , Bilal Piot , Olivier Pietquin

Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations. However, it traditionally requires repeatedly solving a computationally expensive reinforcement learning (RL) problem in…

Machine Learning · Computer Science 2024-02-09 David Wu , Gokul Swamy , J. Andrew Bagnell , Zhiwei Steven Wu , Sanjiban Choudhury

Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation…

Machine Learning · Computer Science 2020-10-23 Ruosong Wang , Dean P. Foster , Sham M. Kakade

Behavior Foundation Models (BFMs) are capable of retrieving high-performing policy for any reward function specified directly at test-time, commonly referred to as zero-shot reinforcement learning (RL). While this is a very efficient…

Machine Learning · Computer Science 2026-03-03 Thomas Rupf , Marco Bagatella , Marin Vlastelica , Andreas Krause

In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value…

Machine Learning · Computer Science 2021-03-02 Hongchang Zhang , Jianzhun Shao , Yuhang Jiang , Shuncheng He , Xiangyang Ji

Motivated by the success of ensembles for uncertainty estimation in supervised learning, we take a renewed look at how ensembles of $Q$-functions can be leveraged as the primary source of pessimism for offline reinforcement learning (RL).…

Machine Learning · Computer Science 2022-05-30 Seyed Kamyar Seyed Ghasemipour , Shixiang Shane Gu , Ofir Nachum

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…

Machine Learning · Computer Science 2023-10-27 Lequn Wang , Akshay Krishnamurthy , Aleksandrs Slivkins

Offline Reinforcement Learning (RL) aims at learning an optimal control from a fixed dataset, without interactions with the system. An agent in this setting should avoid selecting actions whose consequences cannot be predicted from the…

Optimal probabilistic approach in reinforcement learning is computationally infeasible. Its simplification consisting in neglecting difference between true environment and its model estimated using limited number of observations causes…

Artificial Intelligence · Computer Science 2013-06-26 Sergey Rodionov , Alexey Potapov , Yurii Vinogradov

Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to…

Machine Learning · Computer Science 2021-01-05 Qiang He , Xinwen Hou

Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due…

Machine Learning · Computer Science 2025-05-27 Qin-Wen Luo , Ming-Kun Xie , Ye-Wen Wang , Sheng-Jun Huang

Current approaches to model-based offline reinforcement learning often incorporate uncertainty-based reward penalization to address the distributional shift problem. These approaches, commonly known as pessimistic value iteration, use Monte…

Machine Learning · Computer Science 2025-01-17 Abdullah Akgül , Manuel Haußmann , Melih Kandemir

Offline reinforcement learning (RL) enables effective learning from previously collected data without exploration, which shows great promise in real-world applications when exploration is expensive or even infeasible. The discount factor,…

Machine Learning · Computer Science 2022-06-16 Hao Hu , Yiqin Yang , Qianchuan Zhao , Chongjie Zhang

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions…

Machine Learning · Computer Science 2020-07-23 Yao Liu , Adith Swaminathan , Alekh Agarwal , Emma Brunskill

We study whether a risk-sensitive objective from asset-pricing theory -- recursive utility -- improves reinforcement learning for portfolio allocation. The Bellman equation under recursive utility involves a certainty equivalent (CE) of…

General Finance · Quantitative Finance 2026-03-25 Minkey Chang

Offline reinforcement learning (RL) faces a significant challenge of distribution shift. Model-free offline RL penalizes the Q value for out-of-distribution (OOD) data or constrains the policy closed to the behavior policy to tackle this…

Machine Learning · Computer Science 2024-04-18 Xiao-Yin Liu , Xiao-Hu Zhou , Guotao Li , Hao Li , Mei-Jiang Gui , Tian-Yu Xiang , De-Xing Huang , Zeng-Guang Hou

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected data. However, it faces challenges of distributional shift, where the learned policy may encounter unseen scenarios not covered in the offline data.…

Machine Learning · Computer Science 2025-05-27 Jin Zhu , Xin Zhou , Jiaang Yao , Gholamali Aminian , Omar Rivasplata , Simon Little , Lexin Li , Chengchun Shi

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature,…

Machine Learning · Computer Science 2023-03-02 Wei Xiong , Han Zhong , Chengshuai Shi , Cong Shen , Liwei Wang , Tong Zhang

In real-world scenarios, datasets collected from randomized experiments are often constrained by size, due to limitations in time and budget. As a result, leveraging large observational datasets becomes a more attractive option for…

Machine Learning · Statistics 2024-03-19 Danyang Wang , Chengchun Shi , Shikai Luo , Will Wei Sun

We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making…

Machine Learning · Computer Science 2023-09-28 Germano Gabbianelli , Gergely Neu , Matteo Papini