English
Related papers

Related papers: Extending Differential Temporal Difference Methods…

200 papers

Test-time compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs). Despite the empirical success of methods such as best-of-$n$ (BoN) sampling and sequential revision, their fundamental limits…

Machine Learning · Computer Science 2025-12-05 Yue Yu , Qiwei Di , Quanquan Gu , Dongruo Zhou

The temporal-difference methods TD($\lambda$) and Sarsa($\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their…

Artificial Intelligence · Computer Science 2016-09-09 Harm van Seijen , A. Rupam Mahmood , Patrick M. Pilarski , Marlos C. Machado , Richard S. Sutton

In reinforcement learning (RL), continuing tasks refer to tasks where the agent-environment interaction is ongoing and can not be broken down into episodes. These tasks are suitable when environment resets are unavailable, agent-controlled,…

Artificial Intelligence · Computer Science 2025-01-14 Yi Wan , Dmytro Korenkevych , Zheqing Zhu

The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a…

Machine Learning · Computer Science 2026-03-24 Juan Sebastian Rojas , Chi-Guhn Lee

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson

Linear temporal logic (LTL) and, more generally, $\omega$-regular objectives are alternatives to the traditional discount sum and average reward objectives in reinforcement learning (RL), offering the advantage of greater comprehensibility…

Machine Learning · Computer Science 2024-10-17 Xuan-Bach Le , Dominik Wagner , Leon Witzman , Alexander Rabinovich , Luke Ong

This paper introduces a method for constructing an upper bound for exploration policy using either the weighted variance of return sequences or the weighted temporal difference (TD) error. We demonstrate that the variance of the return…

Machine Learning · Computer Science 2020-11-18 Zerong Xi , Gita Sukthankar

Temporal-Difference learning (TD) [Sutton, 1988] with function approximation can converge to solutions that are worse than those obtained by Monte-Carlo regression, even in the simple case of on-policy evaluation. To increase our…

Machine Learning · Computer Science 2018-07-10 Hugo Penedones , Damien Vincent , Hartmut Maennel , Sylvain Gelly , Timothy Mann , Andre Barreto

With the rapid development of vision tasks and the scaling on datasets and models, redundancy reduction in vision datasets has become a key area of research. To address this issue, dataset distillation (DD) has emerged as a promising…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Yinjie Zhao , Heng Zhao , Bihan Wen , Yew-Soon Ong , Joey Tianyi Zhou

Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as…

Machine Learning · Computer Science 2021-11-02 Xiaoteng Ma , Xiaohang Tang , Li Xia , Jun Yang , Qianchuan Zhao

Gradient descent or its variants are popular in training neural networks. However, in deep Q-learning with neural network approximation, a type of reinforcement learning, gradient descent (also known as Residual Gradient (RG)) is barely…

Machine Learning · Computer Science 2022-11-15 Shuyu Yin , Tao Luo , Peilin Liu , Zhi-Qin John Xu

In many RL applications, once training ends, it is vital to detect any deterioration in the agent performance as soon as possible. Furthermore, it often has to be done without modifying the policy and under minimal assumptions regarding the…

Machine Learning · Computer Science 2021-11-01 Ido Greenberg , Shie Mannor

Since the earliest days of reinforcement learning, the workhorse method for assigning credit to actions over time has been temporal-difference (TD) learning, which propagates credit backward timestep-by-timestep. This approach suffers when…

Machine Learning · Computer Science 2021-02-25 David Raposo , Sam Ritter , Adam Santoro , Greg Wayne , Theophane Weber , Matt Botvinick , Hado van Hasselt , Francis Song

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…

Machine Learning · Computer Science 2026-01-26 Chengyang Ying , Xinning Zhou , Zhongkai Hao , Hang Su , Songming Liu , Dong Yan , Jun Zhu

In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates extended training periods and may potentially impede modeling flexibility and capacity. To counteract…

Machine Learning · Computer Science 2023-06-06 Etrit Haxholli , Marco Lorenzi

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated…

Machine Learning · Computer Science 2023-08-22 Akash Velu , Skanda Vaidyanath , Dilip Arumugam

In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted…

Machine Learning · Statistics 2025-05-14 Yang Peng , Kaicheng Jin , Liangyu Zhang , Zhihua Zhang

In multi-vehicle cooperative driving tasks involving high-frequency continuous control, traditional state-based reward functions suffer from the issue of vanishing reward differences. This phenomenon results in a low signal-to-noise ratio…

Artificial Intelligence · Computer Science 2025-11-24 Ye Han , Lijun Zhang , Dejian Meng , Zhuang Zhang

We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations…

Machine Learning · Computer Science 2025-12-18 Hanqing Jin , Renyuan Xu , Yanzhao Yang

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Takehiro Aoshima , Yusuke Shinohara , Byeongseon Park