English
Related papers

Related papers: Long-Horizon Q-Learning: Accurate Value Learning v…

200 papers

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

Machine Learning · Computer Science 2025-04-21 Han-Dong Lim , Donghwan Lee

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be…

Machine Learning · Computer Science 2026-03-17 Mumuksh Tayal , Manan Tayal , Ravi Prakash

We explore fixed-horizon temporal difference (TD) methods, reinforcement learning algorithms for a new kind of value function that predicts the sum of rewards over a $\textit{fixed}$ number of future time steps. To learn the value function…

Machine Learning · Computer Science 2020-02-12 Kristopher De Asis , Alan Chan , Silviu Pitis , Richard S. Sutton , Daniel Graves

Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted…

Machine Learning · Computer Science 2026-02-03 Jiamin Xu , Kyra Gan

Reinforcement learning is a popular method of finding optimal solutions to complex problems. Algorithms like Q-learning excel at learning to solve stochastic problems without a model of their environment. However, they take longer to solve…

Artificial Intelligence · Computer Science 2024-04-25 Jan Diekhoff , Jörn Fischer

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an…

Machine Learning · Computer Science 2021-02-03 Rong Zhu , Mattia Rigotti

Reinforcement Learning (RL) has opened up new opportunities to enhance existing smart systems that generally include a complex decision-making process. However, modern RL algorithms, e.g., Deep Q-Networks (DQN), are based on deep neural…

Machine Learning · Computer Science 2023-06-22 Yang Ni , Danny Abraham , Mariam Issa , Yeseong Kim , Pietro Mercati , Mohsen Imani

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

Machine Learning · Computer Science 2021-02-09 Youngmin Oh , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon tasks remains…

Machine Learning · Computer Science 2026-05-26 Hyungkyu Kang , Byeongchan Kim , Min-hwan Oh

Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods…

Machine Learning · Computer Science 2025-03-18 Kun Wu , Yinuo Zhao , Zhiyuan Xu , Zhengping Che , Chengxiang Yin , Chi Harold Liu , Feiferi Feng , Jian Tang

Offline reinforcement learning seeks to derive improved policies entirely from historical data but often struggles with over-optimistic value estimates for out-of-distribution (OOD) actions. This issue is typically mitigated via policy…

Machine Learning · Computer Science 2025-05-20 Wenhui Liu , Zhijian Wu , Jingchao Wang , Dingjiang Huang , Shuigeng Zhou

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL…

Machine Learning · Computer Science 2025-05-27 Seohong Park , Qiyang Li , Sergey Levine

Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new…

Machine Learning · Computer Science 2017-04-10 Brendan O'Donoghue , Remi Munos , Koray Kavukcuoglu , Volodymyr Mnih

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave…

Machine Learning · Computer Science 2024-01-23 Mitsuhiko Nakamoto , Yuexiang Zhai , Anikait Singh , Max Sobol Mark , Yi Ma , Chelsea Finn , Aviral Kumar , Sergey Levine

Offline Goal-Conditioned Reinforcement Learning seeks to train agents to reach specified goals from previously collected trajectories. Scaling that promises to long-horizon tasks remains challenging, notably due to compounding…

Machine Learning · Computer Science 2026-02-02 Anthony Kobanda , Waris Radji , Mathieu Petitbois , Odalric-Ambrym Maillard , Rémy Portelas

Offline inverse reinforcement learning (IRL) aims to recover a reward function that explains expert behavior using only fixed demonstration data, without any additional online interaction. We propose BiCQL-ML, a policy-free offline IRL…

Machine Learning · Computer Science 2025-12-01 Junsung Park

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

In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…

Machine Learning · Computer Science 2020-09-15 Gabriel Kalweit , Maria Huegle , Moritz Werling , Joschka Boedecker

Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach…

Machine Learning · Computer Science 2025-08-28 Antonio Guillen-Perez

We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation model endowed with in-context learning capabilities. The key…

Machine Learning · Computer Science 2026-05-20 Qisai Liu , Zhanhong Jiang , Timilehin Ayanlade , Ashutosh Kumar Nirala , Yang Li , Aditya Balu , Soumik Sarkar