English
Related papers

Related papers: Why Target Networks Stabilise Temporal Difference …

200 papers

The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal…

Machine Learning · Computer Science 2019-09-24 Donghwan Lee , Niao He

The deadly triad refers to the instability of a reinforcement learning algorithm when it employs off-policy learning, function approximation, and bootstrapping simultaneously. In this paper, we investigate the target network as a tool for…

Machine Learning · Computer Science 2023-10-02 Shangtong Zhang , Hengshuai Yao , Shimon Whiteson

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Machine Learning · Computer Science 2018-11-07 Jalaj Bhandari , Daniel Russo , Raghav Singal

We introduce a generalization of temporal-difference (TD) learning to networks of interrelated predictions. Rather than relating a single prediction to itself at a later time, as in conventional TD methods, a TD network relates each…

Machine Learning · Computer Science 2015-04-22 Richard S. Sutton , Brian Tanner

The use of target networks is a common practice in deep reinforcement learning for stabilizing the training; however, theoretical understanding of this technique is still limited. In this paper, we study the so-called periodic Q-learning…

Machine Learning · Computer Science 2020-02-25 Donghwan Lee , Niao He

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized…

Machine Learning · Computer Science 2025-06-24 Hwanwoo Kim , Panos Toulis , Eric Laber

Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower…

Machine Learning · Computer Science 2026-05-20 Leonard S. Pleiss , James Harrison , Maximilian Schiffer

The target network update frequency (TUF) is a central stabilization mechanism in (deep) Q-learning. However, their selection remains poorly understood and is often treated merely as another tunable hyperparameter rather than as a…

Machine Learning · Computer Science 2026-02-05 Simon Weissmann , Tilman Aach , Benedikt Wille , Sebastian Kassing , Leif Döring

The goal of this manuscript is to conduct a controltheoretic analysis of Temporal Difference (TD) learning algorithms. TD-learning serves as a cornerstone in the realm of reinforcement learning, offering a methodology for approximating the…

Artificial Intelligence · Computer Science 2023-09-12 Donghwan Lee , Do Wan Kim

Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms can become unstable when combined with function approximation…

Machine Learning · Computer Science 2021-06-23 Ray Jiang , Tom Zahavy , Zhongwen Xu , Adam White , Matteo Hessel , Charles Blundell , Hado van Hasselt

Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with…

Machine Learning · Computer Science 2012-05-14 Christopher M. Vigorito

Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the…

Machine Learning · Computer Science 2026-05-15 Théo Vincent , Kevin Gerhardt , Yogesh Tripathi , Habib Maraqten , Adam White , Martha White , Jan Peters , Carlo D'Eramo

Temporal difference (TD) learning is a cornerstone reinforcement learning (RL) method for policy evaluation, where the goal is to estimate the value function of a Markov decision process under a fixed policy. While a substantial body of…

Machine Learning · Computer Science 2026-02-02 Donghwan Lee , Do Wan Kim

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to…

Machine Learning · Computer Science 2020-04-16 Qi Cai , Zhuoran Yang , Jason D. Lee , Zhaoran Wang

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

We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition…

Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

Given a dataset on actions and resulting long-term rewards, a direct estimation approach fits value functions that minimize prediction error on the training data. Temporal difference learning (TD) methods instead fit value functions by…

Machine Learning · Computer Science 2024-02-15 David Cheikhi , Daniel Russo

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning. Despite these…

‹ Prev 1 2 3 10 Next ›