English
Related papers

Related papers: Averaging $n$-step Returns Reduces Variance in Rei…

200 papers

In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's behavior. Existing algorithms for constrained RL (CRL) rely on…

Machine Learning · Computer Science 2023-03-07 Ted Moskovitz , Brendan O'Donoghue , Vivek Veeriah , Sebastian Flennerhag , Satinder Singh , Tom Zahavy

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Machine Learning · Computer Science 2021-03-02 Zichuan Lin , Garrett Thomas , Guangwen Yang , Tengyu Ma

Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the next-token in a sequence, with reinforcement learning…

Machine Learning · Computer Science 2025-12-18 Nikolaos Tsilivis , Eran Malach , Karen Ullrich , Julia Kempe

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement…

Robotics · Computer Science 2025-09-12 Yongkai Tian , Yirong Qi , Xin Yu , Wenjun Wu , Jie Luo

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

Machine Learning · Computer Science 2024-02-12 Somjit Nath , Rushiv Arora , Samira Ebrahimi Kahou

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for…

Machine Learning · Computer Science 2026-04-07 Yaoze Guo , Shana Moothedath

In limited-data settings, a single endpoint mean of an evaluation metric such as the Continuous Ranked Probability Score (CRPS) is itself a random variable, yet it is routinely reported as if it were a stable property of the method. We…

Machine Learning · Computer Science 2026-04-28 Qishi Zhan , Minxuan Hu , Liang He , Guansu Wang , Jiaxin Liu

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Machine Learning · Computer Science 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Traditional portfolio management methods can incorporate specific investor preferences but rely on accurate forecasts of asset returns and covariances. Reinforcement learning (RL) methods do not rely on these explicit forecasts and are…

Portfolio Management · Quantitative Finance 2022-03-23 Ruan Pretorius , Terence van Zyl

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks. Skill learning offers one way of identifying these regularities by decomposing pre-collected…

Machine Learning · Computer Science 2022-12-12 Yiding Jiang , Evan Zheran Liu , Benjamin Eysenbach , Zico Kolter , Chelsea Finn

Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In this work, we develop a novel recipe for their finite sample…

Artificial Intelligence · Computer Science 2018-06-06 Gal Dalal , Balazs Szorenyi , Gugan Thoppe , Shie Mannor

In empirical risk optimization, it has been observed that stochastic gradient implementations that rely on random reshuffling of the data achieve better performance than implementations that rely on sampling the data uniformly. Recent works…

Machine Learning · Computer Science 2019-01-30 Bicheng Ying , Kun Yuan , Stefan Vlaski , Ali H. Sayed

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Computation and Language · Computer Science 2025-12-24 Xiang Chen , Yixin Ou , Quan Feng , Lei Li , Piji Li , Haibo Ye , Sheng-Jun Huang , Shuofei Qiao , Shumin Deng , Huajun Chen , Ningyu Zhang

Many testing problems are readily amenable to randomised tests such as those employing data splitting. However despite their usefulness in principle, randomised tests have obvious drawbacks. Firstly, two analyses of the same dataset may…

Methodology · Statistics 2024-09-05 F. Richard Guo , Rajen D. Shah

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…

Artificial Intelligence · Computer Science 2022-09-29 Thommen George Karimpanal , Roland Bouffanais

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To address this, some methods propose replaying data from previous…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Chenyang Wang , Junjun Jiang , Xingyu Hu , Xianming Liu , Xiangyang Ji

In this era of big data, feature selection techniques, which have long been proven to simplify the model, makes the model more comprehensible, speed up the process of learning, have become more and more important. Among many developed…

Machine Learning · Statistics 2019-11-20 Thu Nguyen

We analyze the convergence rate of the random reshuffling (RR) method, which is a randomized first-order incremental algorithm for minimizing a finite sum of convex component functions. RR proceeds in cycles, picking a uniformly random…

Optimization and Control · Mathematics 2022-02-09 Mert Gürbüzbalaban , Asuman Ozdaglar , Pablo Parrilo

Classical theory in reinforcement learning (RL) predominantly focuses on the single task setting, where an agent learns to solve a task through trial-and-error experience, given access to data only from that task. However, many recent…

Machine Learning · Computer Science 2022-06-28 Aldo Pacchiano , Ofir Nachum , Nilseh Tripuraneni , Peter Bartlett