English
Related papers

Related papers: Offline Policy Comparison with Confidence: Benchma…

200 papers

In practice, it is essential to compare and rank candidate policies offline before real-world deployment for safety and reliability. Prior work seeks to solve this offline policy ranking (OPR) problem through value-based methods, such as…

Machine Learning · Computer Science 2023-12-20 Longchao Da , Porter Jenkins , Trevor Schwantes , Jeffrey Dotson , Hua Wei

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as search engines, recommender systems, and etc. While the…

Machine Learning · Computer Science 2023-09-28 Xiaoying Zhang , Junpu Chen , Hongning Wang , Hong Xie , Yang Liu , John C. S. Lui , Hang Li

Off-policy evaluation (OPE) in contextual bandits has seen rapid adoption in real-world systems, since it enables offline evaluation of new policies using only historic log data. Unfortunately, when the number of actions is large, existing…

Machine Learning · Computer Science 2022-06-17 Yuta Saito , Thorsten Joachims

Off-policy policy evaluation methods for sequential decision making can be used to help identify if a proposed decision policy is better than a current baseline policy. However, a new decision policy may be better than a baseline policy for…

Machine Learning · Computer Science 2021-11-30 Ramtin Keramati , Omer Gottesman , Leo Anthony Celi , Finale Doshi-Velez , Emma Brunskill

Large-scale Web-based services present opportunities for improving UI policies based on observed user interactions. We address challenges of learning such policies through model-free offline Reinforcement Learning (RL) with off-policy…

Predictive models are often introduced to decision-making tasks under the rationale that they improve performance over an existing decision-making policy. However, it is challenging to compare predictive performance against an existing…

Machine Learning · Computer Science 2024-06-13 Luke Guerdan , Amanda Coston , Kenneth Holstein , Zhiwei Steven Wu

Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…

Machine Learning · Computer Science 2025-12-30 Adam Jelley , Trevor McInroe , Sam Devlin , Amos Storkey

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

We develop a generic data-driven method for estimator selection in off-policy policy evaluation settings. We establish a strong performance guarantee for the method, showing that it is competitive with the oracle estimator, up to a constant…

Machine Learning · Computer Science 2020-08-25 Yi Su , Pavithra Srinath , Akshay Krishnamurthy

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2022-02-18 Daniel Shin , Daniel S. Brown , Anca D. Dragan

Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However,…

Machine Learning · Computer Science 2022-09-01 Marco Bagatella , Sammy Christen , Otmar Hilliges

In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches. Although straightforward, these techniques in general yield…

Machine Learning · Computer Science 2020-07-28 Ilya Kostrikov , Ofir Nachum

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the foundation of many offline RL algorithms. Behavior estimation aims…

Machine Learning · Computer Science 2023-05-29 Guoxi Zhang , Hisashi Kashima

We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function…

Machine Learning · Computer Science 2022-06-16 Jinglin Chen , Nan Jiang

Offline reinforcement learning (offline RL) considers problems where learning is performed using only previously collected samples and is helpful for the settings in which collecting new data is costly or risky. In model-based offline RL,…

Machine Learning · Computer Science 2023-03-09 Mustafa O. Karabag , Ufuk Topcu

Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the policy and the offline…

Machine Learning · Computer Science 2021-10-15 Haoran Xu , Xianyuan Zhan , Jianxiong Li , Honglei Yin

We study model-based offline Reinforcement Learning with general function approximation without a full coverage assumption on the offline data distribution. We present an algorithm named Constrained Pessimistic Policy Optimization…

Machine Learning · Computer Science 2023-01-11 Masatoshi Uehara , Wen Sun

Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. However, a public benchmark with appropriate performance metrics for…

Machine Learning · Statistics 2021-04-12 Jan-Matthis Lueckmann , Jan Boelts , David S. Greenberg , Pedro J. Gonçalves , Jakob H. Macke
‹ Prev 1 4 5 6 7 8 10 Next ›