English
Related papers

Related papers: Directly Estimating the Variance of the {\lambda}-…

200 papers

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

This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes. Oftentimes,…

Optimization and Control · Mathematics 2021-10-12 Tao Sun , Han Shen , Tianyi Chen , Dongsheng Li

In many computational science and engineering applications, the output of a system of interest corresponding to a given input can be queried at different levels of fidelity with different costs. Typically, low-fidelity data is cheap and…

Machine Learning · Computer Science 2022-06-13 Sami Khairy , Prasanna Balaprakash

We study the use of Temporal-Difference learning for estimating the structural parameters in dynamic discrete choice models. Our algorithms are based on the conditional choice probability approach but use functional approximations to…

Econometrics · Economics 2022-12-23 Karun Adusumilli , Dita Eckardt

Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly…

Machine Learning · Computer Science 2019-05-24 Pierre Thodoroff , Nishanth Anand , Lucas Caccia , Doina Precup , Joelle Pineau

Recent advances in recommender systems have shown that user-system interaction essentially formulates long-term optimization problems, and online reinforcement learning can be adopted to improve recommendation performance. The general…

Information Retrieval · Computer Science 2025-02-04 Xiaobei Wang , Shuchang Liu , Qingpeng Cai , Xiang Li , Lantao Hu , Han li , Guangming Xie

Differential temporal difference (TD) methods are value-based reinforcement learning algorithms that have been proposed for infinite-horizon problems. They rely on reward centering, where each reward is centered by the average reward. This…

Machine Learning · Computer Science 2026-05-07 Kris De Asis , Mohamed Elsayed , Jiamin He

Balancing between computational efficiency and sample efficiency is an important goal in reinforcement learning. Temporal difference (TD) learning algorithms stochastically update the value function, with a linear time complexity in the…

Machine Learning · Computer Science 2016-11-21 Clement Gehring , Yangchen Pan , Martha White

Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true…

Machine Learning · Computer Science 2017-04-21 Bo Liu , Daoming Lyu , Wen Dong , Saad Biaz

Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques. Computation of the solution to…

Machine Learning · Computer Science 2020-03-02 Adithya M. Devraj , Ioannis Kontoyiannis , Sean P. Meyn

In this paper, a new reinforcement learning (RL) method known as the method of temporal differential is introduced. Compared to the traditional temporal-difference learning method, it plays a crucial role in developing novel RL techniques…

Machine Learning · Computer Science 2020-06-02 Tao Bian , Zhong-Ping Jiang

Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of…

Machine Learning · Computer Science 2018-11-09 Joshua Romoff , Peter Henderson , Alexandre Piché , Vincent Francois-Lavet , Joelle Pineau

We extend temporal-difference (TD) learning in order to obtain risk-sensitive, model-free reinforcement learning algorithms. This extension can be regarded as modification of the Rescorla-Wagner rule, where the (sigmoidal) stimulus is taken…

Machine Learning · Computer Science 2021-11-05 Grégoire Delétang , Jordi Grau-Moya , Markus Kunesch , Tim Genewein , Rob Brekelmans , Shane Legg , Pedro A. Ortega

We propose a unified framework to study policy evaluation (PE) and the associated temporal difference (TD) methods for reinforcement learning in continuous time and space. We show that PE is equivalent to maintaining the martingale…

Machine Learning · Computer Science 2022-02-02 Yanwei Jia , Xun Yu Zhou

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

In reinforcement learning, the discount factor $\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become…

Machine Learning · Computer Science 2020-06-24 Chen Tessler , Shie Mannor

This study investigates the mean-variance (MV) trade-off in reinforcement learning (RL), an instance of the sequential decision-making under uncertainty. Our objective is to obtain MV-efficient policies whose means and variances are located…

Machine Learning · Computer Science 2024-11-14 Masahiro Kato , Kei Nakagawa , Kenshi Abe , Tetsuro Morimura , Kentaro Baba

Future reward estimation is a core component of reinforcement learning agents; i.e., Q-value and state-value functions, predicting an agent's sum of future rewards. Their scalar output, however, obfuscates when or what individual future…

Artificial Intelligence · Computer Science 2024-08-16 Mark Towers , Yali Du , Christopher Freeman , Timothy J. Norman

Temporal difference (TD) learning is a popular algorithm for policy evaluation in reinforcement learning, but the vanilla TD can substantially suffer from the inherent optimization variance. A variance reduced TD (VRTD) algorithm was…

Machine Learning · Computer Science 2020-01-13 Tengyu Xu , Zhe Wang , Yi Zhou , Yingbin Liang

Value functions arise as a component of algorithms as well as performance metrics in statistics and engineering applications. Computation of the associated Bellman equations is numerically challenging in all but a few special cases. A…

Systems and Control · Computer Science 2018-12-27 Adithya M. Devraj , Sean P. Meyn