English
Related papers

Related papers: Implicit Updates for Average-Reward Temporal Diffe…

200 papers

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

Emphatic temporal difference (ETD) learning (Sutton et al., 2016) is a successful method to conduct the off-policy value function evaluation with function approximation. Although ETD has been shown to converge asymptotically to a desirable…

Machine Learning · Computer Science 2022-07-18 Ziwei Guan , Tengyu Xu , Yingbin Liang

Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning under off-policy…

Artificial Intelligence · Computer Science 2019-03-04 Xiang Gu , Sina Ghiassian , Richard S. Sutton

Recent advances in reinforcement learning (RL) have renewed interest in reward design for shaping agent behavior, but manually crafting reward functions is tedious and error-prone. A principled alternative is to specify behavioral…

Artificial Intelligence · Computer Science 2026-03-23 Milad Kazemi , Mateo Perez , Fabio Somenzi , Sadegh Soudjani , Ashutosh Trivedi , Alvaro Velasquez

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

We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications, reinforcement learning (RL) is complicated by the fact that…

Machine Learning · Computer Science 2015-03-17 Byron Boots , Geoffrey J. Gordon

Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely…

Computation and Language · Computer Science 2025-09-30 Xiaoqian Liu , Ke Wang , Yuchuan Wu , Fei Huang , Yongbin Li , Junge Zhang , Jianbin Jiao

We study non-rectangular robust Markov decision processes under the average-reward criterion, where the ambiguity set couples transition probabilities across states and the adversary commits to a stationary kernel for the entire horizon. We…

Optimization and Control · Mathematics 2026-03-11 Shengbo Wang , Nian Si

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$.…

Machine Learning · Statistics 2025-01-17 Yang Peng , Liangyu Zhang , Zhihua Zhang

Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple…

Machine Learning · Computer Science 2026-02-27 Dhiraj Neupane , Richard Dazeley , Mohamed Reda Bouadjenek , Sunil Aryal

We consider the problem of reward learning for temporally extended tasks. For reward learning, inverse reinforcement learning (IRL) is a widely used paradigm. Given a Markov decision process (MDP) and a set of demonstrations for a task, IRL…

Robotics · Computer Science 2021-07-14 Farzan Memarian , Zhe Xu , Bo Wu , Min Wen , Ufuk Topcu

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 this paper we present the first empirical study of the emphatic temporal-difference learning algorithm (ETD), comparing it with conventional temporal-difference learning, in particular, with linear TD(0), on on-policy and off-policy…

Artificial Intelligence · Computer Science 2017-05-15 Sina Ghiassian , Banafsheh Rafiee , Richard S. Sutton

We propose an observation-driven modeling framework that allows model parameters to vary over time through an implicit score-driven (ISD) update. The ISD update maximizes the logarithmic observation density with respect to the parameter…

Methodology · Statistics 2026-04-21 Rutger-Jan Lange , Bram van Os , Dick van Dijk

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

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 experimenting with off-policy temporal difference (TD) methods in hierarchical reinforcement learning (HRL) systems, we have observed unwanted on-policy learning under reproducible conditions. Here we present modifications to several TD…

Machine Learning · Computer Science 2015-03-19 Mitchell Keith Bloch

Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem,…

Computer Vision and Pattern Recognition · Computer Science 2018-10-05 Ghouthi Boukli Hacene , Vincent Gripon , Nicolas Farrugia , Matthieu Arzel , Michel Jezequel

Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as…

Machine Learning · Computer Science 2021-07-13 Ray Jiang , Shangtong Zhang , Veronica Chelu , Adam White , 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