English
Related papers

Related papers: Towards Parameter-Free Temporal Difference Learnin…

200 papers

Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such…

Machine Learning · Computer Science 2020-02-25 Vitchyr Pong , Shixiang Gu , Murtaza Dalal , Sergey Levine

We consider the dynamics of a linear stochastic approximation algorithm driven by Markovian noise, and derive finite-time bounds on the moments of the error, i.e., deviation of the output of the algorithm from the equilibrium point of an…

Machine Learning · Computer Science 2019-03-11 R. Srikant , Lei Ying

Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators. These results suggest that RL methods that…

Machine Learning · Computer Science 2018-06-05 Artemij Amiranashvili , Alexey Dosovitskiy , Vladlen Koltun , Thomas Brox

Fast-converging algorithms are a contemporary requirement in reinforcement learning. In the context of linear function approximation, the magnitude of the smallest eigenvalue of the key matrix is a major factor reflecting the convergence…

Machine Learning · Computer Science 2024-11-12 Xingguo Chen , Yu Gong , Shangdong Yang , Wenhao Wang

In many finite horizon episodic reinforcement learning (RL) settings, it is desirable to optimize for the undiscounted return - in settings like Atari, for instance, the goal is to collect the most points while staying alive in the long…

Machine Learning · Computer Science 2019-05-28 Joshua Romoff , Peter Henderson , Ahmed Touati , Emma Brunskill , Joelle Pineau , Yann Ollivier

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

We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this…

Machine Learning · Computer Science 2023-05-31 Mark Rowland , Yunhao Tang , Clare Lyle , Rémi Munos , Marc G. Bellemare , Will Dabney

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervised learning, the regime of over-parameterization and its…

Machine Learning · Computer Science 2024-02-20 David Brellmann , Eloïse Berthier , David Filliat , Goran Frehse

In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD)…

Machine Learning · Computer Science 2022-04-22 Xingang Guo , Bin Hu

We study the convergence of off-policy TD(0) with linear function approximation when used to approximate the expected discounted reward in a Markov chain. It is well known that the combination of off-policy learning and function…

Machine Learning · Statistics 2026-04-02 Maik Overmars , Jasper Goseling , Richard Boucherie

Non-Markovian dynamics are commonly found in real-world environments due to long-range dependencies, partial observability, and memory effects. The Bellman equation that is the central pillar of Reinforcement learning (RL) becomes only…

Machine Learning · Computer Science 2026-02-09 Zuyuan Zhang , Sizhe Tang , Tian Lan

To estimate the value functions of policies from exploratory data, most model-free off-policy algorithms rely on importance sampling, where the use of importance sampling ratios often leads to estimates with severe variance. It is thus…

Machine Learning · Computer Science 2017-02-13 Ashique Rupam Mahmood , Huizhen Yu , Richard S. Sutton

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such…

Machine Learning · Computer Science 2025-03-11 Vivek Myers , Chongyi Zheng , Anca Dragan , Sergey Levine , Benjamin Eysenbach

Dynamic Programming suffers from the curse of dimensionality due to large state and action spaces, a challenge further compounded by uncertainties in the environment. To mitigate these issue, we explore an off-policy based Temporal…

Systems and Control · Electrical Eng. & Systems 2025-03-05 Ali Forootani , Raffaele Iervolino , Massimo Tipaldi , Mohammad Khosravi

In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance…

Machine Learning · Computer Science 2013-10-15 Aviv Tamar , Dotan Di Castro , Shie Mannor

Policy mirror descent (PMD) is a general policy optimization framework in reinforcement learning, which can cover a wide range of typical policy optimization methods by specifying different mirror maps. Existing analysis of PMD requires…

Optimization and Control · Mathematics 2025-09-24 Jiacai Liu , Wenye Li , Ke Wei

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value function toward a learning target using value estimates at…

Machine Learning · Computer Science 2022-01-07 Anthony GX-Chen , Veronica Chelu , Blake A. Richards , Joelle Pineau

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

In a broad class of reinforcement learning applications, stochastic rewards have heavy-tailed distributions, which lead to infinite second-order moments for stochastic (semi)gradients in policy evaluation and direct policy optimization. In…

Machine Learning · Computer Science 2023-06-21 Semih Cayci , Atilla Eryilmaz

Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents. However, many existing FedRL algorithms assume that all agents operate in identical…

Machine Learning · Computer Science 2025-06-17 Ali Beikmohammadi , Sarit Khirirat , Peter Richtárik , Sindri Magnússon