English
Related papers

Related papers: Temporal Difference Learning as Gradient Splitting

200 papers

One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key…

Artificial Intelligence · Computer Science 2016-10-25 Martha White , Adam White

In reinforcement learning, the TD($\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\lambda$) is its sensitivity…

Machine Learning · Statistics 2014-12-23 Aviv Tamar , Panos Toulis , Shie Mannor , Edoardo M. Airoldi

TD($\lambda$) with function approximation has proved empirically successful for some complex reinforcement learning problems. For linear approximation, TD($\lambda$) has been shown to minimise the squared error between the approximate value…

Machine Learning · Computer Science 2025-12-24 Lex Weaver , Jonathan Baxter

Recent non-asymptotic analyses have substantially advanced the theory of distributional policy evaluation, but they largely concern synchronous full-state updates under a generative model, model-based estimators, accelerated variants, or…

Machine Learning · Computer Science 2026-05-11 Ege C. Kaya , Abolfazl Hashemi

The task of predicting long-term patient outcomes using supervised machine learning is a challenging one, in part because of the high variance of each patient's trajectory, which can result in the model over-fitting to the training data.…

Machine Learning · Computer Science 2026-02-09 Thomas Frost , Kezhi Li , Steve Harris

We study the multi-step off-policy learning approach to distributional RL. Despite the apparent similarity between value-based RL and distributional RL, our study reveals intriguing and fundamental differences between the two cases in the…

Machine Learning · Computer Science 2022-07-18 Yunhao Tang , Mark Rowland , Rémi Munos , Bernardo Ávila Pires , Will Dabney , Marc G. Bellemare

How much does a trained RL policy actually use its past observations? We propose \emph{Temporal Range}, a model-agnostic metric that treats first-order sensitivities of multiple vector outputs across a temporal window to the input sequence…

Machine Learning · Computer Science 2025-12-09 Rodney Lafuente-Mercado , Daniela Rus , T. Konstantin Rusch

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the…

Machine Learning · Computer Science 2019-07-16 Harsh Gupta , R. Srikant , Lei Ying

Contrastive divergence (CD) learning is a classical method for fitting unnormalized statistical models to data samples. Despite its wide-spread use, the convergence properties of this algorithm are still not well understood. The main source…

Machine Learning · Computer Science 2021-03-17 Omer Yair , Tomer Michaeli

This paper considers the policy evaluation problem in a multi-agent reinforcement learning (MARL) environment over decentralized and directed networks. The focus is on decentralized temporal difference (TD) learning with linear function…

Optimization and Control · Mathematics 2021-09-01 Zhaoxian Wu , Han Shen , Tianyi Chen , Qing Ling

Linear Temporal Logic (LTL) is a formal way of specifying complex objectives for planning problems modeled as Markov Decision Processes (MDPs). The planning problem aims to find the optimal policy that maximizes the satisfaction probability…

Robotics · Computer Science 2024-08-13 Zetong Xuan , Yu Wang

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe behavior.…

Machine Learning · Computer Science 2025-06-17 Zahra Shahrooei , Ali Baheri

A fundamental notion of distance between train and test distributions from the field of domain adaptation is discrepancy distance. While in general hard to compute, here we provide the first set of provably efficient algorithms for testing…

Data Structures and Algorithms · Computer Science 2024-06-14 Gautam Chandrasekaran , Adam R. Klivans , Vasilis Kontonis , Konstantinos Stavropoulos , Arsen Vasilyan

In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms,…

Machine Learning · Computer Science 2021-08-09 Semih Cayci , Siddhartha Satpathi , Niao He , R. Srikant

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Machine Learning · Computer Science 2020-05-19 Mingde Zhao , Sitao Luan , Ian Porada , Xiao-Wen Chang , Doina Precup

This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the…

Machine Learning · Statistics 2015-04-06 Kamil Ciosek

We propose a refinement of temporal-difference learning that enforces first-order Bellman consistency: the learned value function is trained to match not only the Bellman targets in value but also their derivatives with respect to states…

Machine Learning · Computer Science 2025-11-25 Fabian Schramm , Nicolas Perrin-Gilbert , Justin Carpentier

We evaluate the ability of temporal difference learning to track the reward function of a policy as it changes over time. Our results apply a new adiabatic theorem that bounds the mixing time of time-inhomogeneous Markov chains. We derive…

Machine Learning · Computer Science 2020-11-03 Neil Walton

This paper studies the error metric selection for long-term memory learning in sequence modelling. We examine the bias towards short-term memory in commonly used errors, including mean absolute/squared error. Our findings show that all…

Machine Learning · Computer Science 2023-07-24 Shida Wang , Zhanglu Yan

We present on-line policy gradient algorithms for computing the locally optimal policy of a constrained, average cost, finite state Markov Decision Process. The stochastic approximation algorithms require estimation of the gradient of the…

Optimization and Control · Mathematics 2018-12-18 Vikram Krishnamurthy , Felisa Vazquez Abad