English
Related papers

Related papers: Off-policy Distributional Q($\lambda$): Distributi…

200 papers

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…

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

This document should serve as a quick reference for and guide to the implementation of linear GQ($\lambda$), a gradient-based off-policy temporal-difference learning algorithm. Explanation of the intuition and theory behind the algorithm…

Machine Learning · Computer Science 2017-05-12 Adam White , Richard S. Sutton

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

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

Importance sampling is a central idea underlying off-policy prediction in reinforcement learning. It provides a strategy for re-weighting samples from a distribution to obtain unbiased estimates under another distribution. However,…

Machine Learning · Computer Science 2023-06-28 Kristopher De Asis , Eric Graves , Richard S. Sutton

This paper introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages…

Systems and Control · Electrical Eng. & Systems 2023-04-03 Victor G. Lopez , Mohammad Alsalti , Matthias A. Müller

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Machine Learning · Computer Science 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…

Machine Learning · Computer Science 2020-08-20 Aviral Kumar , Aurick Zhou , George Tucker , Sergey Levine

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic and extensive analysis of experience replay in Q-learning…

Machine Learning · Computer Science 2020-07-15 William Fedus , Prajit Ramachandran , Rishabh Agarwal , Yoshua Bengio , Hugo Larochelle , Mark Rowland , Will Dabney

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL. At the…

Optimization and Control · Mathematics 2023-03-27 Zifan Wang , Yulong Gao , Siyi Wang , Michael M. Zavlanos , Alessandro Abate , Karl H. Johansson

In temporal difference (TD) learning, off-policy sampling is known to be more practical than on-policy sampling, and by decoupling learning from data collection, it enables data reuse. It is known that policy evaluation (including…

Machine Learning · Computer Science 2021-06-25 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient…

Machine Learning · Computer Science 2020-08-04 Samuele Tosatto , Joao Carvalho , Hany Abdulsamad , Jan Peters

Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (OOD) data points. To…

Machine Learning · Computer Science 2021-10-06 Gaon An , Seungyong Moon , Jang-Hyun Kim , Hyun Oh Song

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-09-10 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Most offline reinforcement learning (RL) methods suffer from the trade-off between improving the policy to surpass the behavior policy and constraining the policy to limit the deviation from the behavior policy as computing $Q$-values using…

Machine Learning · Computer Science 2023-03-29 Haoran Xu , Li Jiang , Jianxiong Li , Zhuoran Yang , Zhaoran Wang , Victor Wai Kin Chan , Xianyuan Zhan

In this paper, we present a Q-learning algorithm to solve the optimal output regulation problem for discrete-time LTI systems. This off-policy algorithm only relies on using persistently exciting input-output data, measured offline. No…

Systems and Control · Electrical Eng. & Systems 2024-08-21 Mohammad Alsalti , Victor G. Lopez , Matthias A. Müller

Off-policy reinforcement learning holds the promise of sample-efficient learning of decision-making policies by leveraging past experience. However, in the offline RL setting -- where a fixed collection of interactions are provided and no…

Machine Learning · Computer Science 2021-01-15 Seyed Kamyar Seyed Ghasemipour , Dale Schuurmans , Shixiang Shane Gu

Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-ensemble, or better exploration mechanisms. We, instead,…

Machine Learning · Computer Science 2023-05-31 Jiafei Lyu , Le Wan , Zongqing Lu , Xiu Li

When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then using these ratios as rewards in a standard reinforcement…

Machine Learning · Computer Science 2019-12-12 Ilya Kostrikov , Ofir Nachum , Jonathan Tompson