English
Related papers

Related papers: Model-based Offline Imitation Learning with Non-ex…

200 papers

We study the problem of imitating an expert demonstrator in a discrete-time, continuous state-and-action control system. We show that, even if the dynamics satisfy a control-theoretic property called exponential stability (i.e. the effects…

Machine Learning · Computer Science 2025-07-29 Max Simchowitz , Daniel Pfrommer , Ali Jadbabaie

We address policy learning with logged data in contextual bandits. Current offline-policy learning algorithms are mostly based on inverse propensity score (IPS) weighting requiring the logging policy to have \emph{full support} i.e. a…

Machine Learning · Statistics 2021-07-27 Hung Tran-The , Sunil Gupta , Thanh Nguyen-Tang , Santu Rana , Svetha Venkatesh

We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a…

Robotics · Computer Science 2025-10-06 Yilin Wang , Shangzhe Li , Haoyi Niu , Zhiao Huang , Weitong Zhang , Hao Su

Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even…

Machine Learning · Computer Science 2024-03-19 Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman , James Weimer , Insup Lee

Behavior cloning of expert demonstrations can speed up learning optimal policies in a more sample-efficient way over reinforcement learning. However, the policy cannot extrapolate well to unseen states outside of the demonstration data,…

Machine Learning · Computer Science 2022-10-19 Jung Yeon Park , Lawson L. S. Wong

Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert demonstrations bypasses…

Machine Learning · Computer Science 2026-05-19 Sayambhu Sen , Shalabh Bhatnagar

Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as effective initialization for online algorithms, enhancing sample efficiency and speeding up convergence. However, when such…

Machine Learning · Computer Science 2023-12-20 Girolamo Macaluso , Alessandro Sestini , Andrew D. Bagdanov

Data is often generated in streams, with new observations arriving over time. A key challenge for learning models from data streams is capturing relevant information while keeping computational costs manageable. We explore intelligent data…

Machine Learning · Computer Science 2025-12-23 Benedetta Lavinia Mussati , Freddie Bickford Smith , Tom Rainforth , Stephen Roberts

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle…

Machine Learning · Computer Science 2022-06-14 Laixi Shi , Gen Li , Yuting Wei , Yuxin Chen , Yuejie Chi

This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong performance in…

Machine Learning · Computer Science 2024-03-29 Teodor V. Marinov , Alekh Agarwal , Mircea Trofin

We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to…

Machine Learning · Computer Science 2019-01-16 Yifei Ma , Yu-Xiang Wang , Balakrishnan , Narayanaswamy

Overestimation arising from selecting unseen actions during policy evaluation is a major challenge in offline reinforcement learning (RL). A minimalist approach in the single-agent setting -- adding behavior cloning (BC) regularization to…

Machine Learning · Computer Science 2026-02-16 Woojun Kim , Katia Sycara

Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous. To avoid that, one has…

Machine Learning · Computer Science 2024-05-10 Yassine Chemingui , Aryan Deshwal , Trong Nghia Hoang , Janardhan Rao Doppa

Behavioral cloning uses a dataset of demonstrations to learn a policy. To overcome computationally expensive training procedures and address the policy adaptation problem, we propose to use latent spaces of pre-trained foundation models to…

Artificial Intelligence · Computer Science 2024-04-09 Federco Malato , Florian Leopold , Andrew Melnik , Ville Hautamaki

Imitation learning (IL) has proven to be an effective method for learning good policies from expert demonstrations. Adversarial imitation learning (AIL), a subset of IL methods, is particularly promising, but its theoretical foundation in…

Machine Learning · Computer Science 2023-06-14 Tian Xu , Ziniu Li , Yang Yu , Zhi-Quan Luo

Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is…

Machine Learning · Computer Science 2026-01-07 Minsu Kim , Jiayao Gu , Ye Yuan , Taeyoung Yun , Zixuan Liu , Yoshua Bengio , Can Chen

Learning to perform tasks by leveraging a dataset of expert observations, also known as imitation learning from observations (ILO), is an important paradigm for learning skills without access to the expert reward function or the expert…

Machine Learning · Computer Science 2022-04-26 Tanmay Gangwani , Yuan Zhou , Jian Peng

We propose a cumulative oversampling (CO) method for online learning. Our key idea is to sample parameter estimations from the updated belief space once in each round (similar to Thompson Sampling), and utilize the cumulative samples up to…

Machine Learning · Computer Science 2020-09-17 Shatian Wang , Shuoguang Yang , Zhen Xu , Van-Anh Truong

Offline Reinforcement Learning (RL) addresses the problem of sequential decision-making by learning optimal policy through pre-collected data, without interacting with the environment. As yet, it has remained somewhat impractical, because…

Machine Learning · Computer Science 2024-10-07 Maksim Bobrin , Nazar Buzun , Dmitrii Krylov , Dmitry V. Dylov

We study the problem of offline imitation learning in Markov decision processes (MDPs), where the goal is to learn a well-performing policy given a dataset of state-action pairs generated by an expert policy. Complementing a recent line of…

Machine Learning · Computer Science 2026-01-09 Antoine Moulin , Gergely Neu , Luca Viano