English
Related papers

Related papers: SimuDICE: Offline Policy Optimization Through Worl…

200 papers

In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as…

Machine Learning · Statistics 2018-11-20 Zhengyuan Zhou , Susan Athey , Stefan Wager

Reinforcement-learning (RL) agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulators produced by…

Machine Learning · Computer Science 2026-02-05 Arnaud Fickinger , Abderrahim Bendahi , Stuart Russell

We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value…

Econometrics · Economics 2019-07-23 Mert Demirer , Vasilis Syrgkanis , Greg Lewis , Victor Chernozhukov

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

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

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by…

Machine Learning · Computer Science 2024-05-24 Jinxin Liu , Xinghong Guo , Zifeng Zhuang , Donglin Wang

Visual-motor policy learning has advanced with architectures like diffusion-based policies, known for modeling complex robotic trajectories. However, their prolonged inference times hinder high-frequency control tasks requiring real-time…

Robotics · Computer Science 2024-12-20 Bofang Jia , Pengxiang Ding , Can Cui , Mingyang Sun , Pengfang Qian , Siteng Huang , Zhaoxin Fan , Donglin Wang

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Machine Learning · Computer Science 2025-11-12 Debamita Ghosh , George K. Atia , Yue Wang

Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory…

Machine Learning · Computer Science 2023-04-04 Bogdan Mazoure , Jake Bruce , Doina Precup , Rob Fergus , Ankit Anand

Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors present in the training data. In contrast, simulation…

Machine Learning · Computer Science 2024-09-24 Eshagh Kargar , Ville Kyrki

The prevalent use of benchmarks in current offline reinforcement learning (RL) research has led to a neglect of the imbalance of real-world dataset distributions in the development of models. The real-world offline RL dataset is often…

Machine Learning · Computer Science 2024-05-22 Li Jiang , Sijie Cheng , Jielin Qiu , Haoran Xu , Wai Kin Chan , Zhao Ding

In many real-world multi-agent cooperative tasks, due to high cost and risk, agents cannot continuously interact with the environment and collect experiences during learning, but have to learn from offline datasets. However, the transition…

Machine Learning · Computer Science 2023-08-01 Jiechuan Jiang , Zongqing Lu

Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the…

Machine Learning · Computer Science 2023-06-23 Zhang-Wei Hong , Pulkit Agrawal , Rémi Tachet des Combes , Romain Laroche

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase,…

Machine Learning · Computer Science 2024-09-05 Xu-Hui Liu , Tian-Shuo Liu , Shengyi Jiang , Ruifeng Chen , Zhilong Zhang , Xinwei Chen , Yang Yu

Achieving both optimality and safety under unknown system dynamics is a central challenge in real-world deployment of agents. To address this, we introduce a notion of maximum safe dynamics learning, where sufficient exploration is…

Systems and Control · Electrical Eng. & Systems 2026-02-24 Manish Prajapat , Johannes Köhler , Melanie N. Zeilinger , Andreas Krause

Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g.,…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Alexander Khazatsky , Sergey Levine , Ruslan Salakhutdinov

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on…

Machine Learning · Computer Science 2019-10-01 Zhenyu Zhang , Xiangfeng Luo , Tong Liu , Shaorong Xie , Jianshu Wang , Wei Wang , Yang Li , Yan Peng

The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration. One of the main challenges in offline RL is the distribution…

Machine Learning · Computer Science 2023-10-31 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem…

Machine Learning · Computer Science 2024-02-29 Xiao Ma , Bingyi Kang , Zhongwen Xu , Min Lin , Shuicheng Yan