English
Related papers

Related papers: Efficient Offline Reinforcement Learning: First Im…

200 papers

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as…

Machine Learning · Computer Science 2020-06-30 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…

Existing offline reinforcement learning (RL) methods face a few major challenges, particularly the distributional shift between the learned policy and the behavior policy. Offline Meta-RL is emerging as a promising approach to address these…

Machine Learning · Computer Science 2022-07-14 Sen Lin , Jialin Wan , Tengyu Xu , Yingbin Liang , Junshan Zhang

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…

Robotics · Computer Science 2026-05-20 Dongjie Yu , Kun Lei , Zhennan Jiang , Jia Pan , Huazhe Xu

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

Machine Learning · Computer Science 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

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

Reinforcement learning is time-consuming for complex tasks due to the need for large amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym, have sped up data collection thousands of times on a commodity GPU.…

Machine Learning · Computer Science 2023-07-25 Zechu Li , Tao Chen , Zhang-Wei Hong , Anurag Ajay , Pulkit Agrawal

We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions…

Machine Learning · Computer Science 2026-03-19 Yihong Guo , Yu Yang , Pan Xu , Anqi Liu

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

Machine Learning · Computer Science 2026-03-03 Daniel Ritter , Owen Oertell , Bradley Guo , Jonathan Chang , Kianté Brantley , Wen Sun

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling…

In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in…

Machine Learning · Computer Science 2026-02-11 Prajwal Koirala , Zhanhong Jiang , Soumik Sarkar , Cody Fleming

Many practical applications of reinforcement learning (RL) constrain the agent to learn from a fixed offline dataset of logged interactions, which has already been gathered, without offering further possibility for data collection. However,…

Machine Learning · Computer Science 2021-07-06 Zizhou Su

Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online…

Machine Learning · Computer Science 2024-03-18 Ishita Mediratta , Qingfei You , Minqi Jiang , Roberta Raileanu

We consider the problem of sequential recommendation, where the current recommendation is made based on past interactions. This recommendation task requires efficient processing of the sequential data and aims to provide recommendations…

Information Retrieval · Computer Science 2023-07-28 Xumei Xi , Yuke Zhao , Quan Liu , Liwen Ouyang , Yang Wu

Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon planning, and settings with sparse rewards. However, learning…

Machine Learning · Computer Science 2025-03-19 Carolin Schmidt , Daniele Gammelli , James Harrison , Marco Pavone , Filipe Rodrigues

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Machine Learning · Computer Science 2021-06-10 Kimin Lee , Laura Smith , Pieter Abbeel

Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data. However,…

Machine Learning · Computer Science 2025-05-20 Haochen Yuan , Minting Pan , Yunbo Wang , Siyu Gao , Philip S. Yu , Xiaokang Yang

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

Machine Learning · Computer Science 2015-03-20 Thomas Degris , Martha White , Richard S. Sutton