English
Related papers

Related papers: Toward Efficient Gradient-Based Value Estimation

200 papers

Reinforcement learning lies at the intersection of several challenges. Many applications of interest involve extremely large state spaces, requiring function approximation to enable tractable computation. In addition, the learner has only a…

Machine Learning · Computer Science 2021-05-11 Andrew Jacobsen , Alan Chan

We study trade-offs between convergence rate and robustness to gradient errors in the context of first-order methods. Our focus is on generalized momentum methods (GMMs)--a broad class that includes Nesterov's accelerated gradient,…

Optimization and Control · Mathematics 2026-01-14 Mert Gürbüzbalaban , Yasa Syed , Necdet Serhat Aybat

Scaling deep reinforcement learning networks is challenging and often results in degraded performance, yet the root causes of this failure mode remain poorly understood. Several recent works have proposed mechanisms to address this, but…

We consider a regularized expected reward optimization problem in the non-oblivious setting that covers many existing problems in reinforcement learning (RL). In order to solve such an optimization problem, we apply and analyze the…

Machine Learning · Computer Science 2024-08-21 Ling Liang , Haizhao Yang

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation…

Machine Learning · Computer Science 2024-10-02 Jesus Garcia Fernandez , Sander Keemink , Marcel van Gerven

In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error…

Machine Learning · Computer Science 2024-03-28 Motoki Omura , Takayuki Osa , Yusuke Mukuta , Tatsuya Harada

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated…

Machine Learning · Computer Science 2022-05-04 Vincent Mai , Kaustubh Mani , Liam Paull

We consider machine learning tasks with low-rank functional tree tensor networks (TTN) as the learning model. While in the case of least-squares regression, low-rank functional TTNs can be efficiently optimized using alternating…

Optimization and Control · Mathematics 2026-04-13 Nikolas Klug , Michael Ulbrich , André Uschmajew , Marius Willner

Many problems involve the use of models which learn probability distributions or incorporate randomness in some way. In such problems, because computing the true expected gradient may be intractable, a gradient estimator is used to update…

Machine Learning · Computer Science 2022-12-29 Ronan Keane , H. Oliver Gao

Mini-batch sub-sampling (MBSS) is favored in deep neural network training to reduce the computational cost. Still, it introduces an inherent sampling error, making the selection of appropriate learning rates challenging. The sampling errors…

Machine Learning · Statistics 2021-05-25 Younghwan Chae , Daniel N. Wilke , Dominic Kafka

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for post-training large reasoning models (LRMs) using policy-gradient methods such as GRPO. To stabilize training, these methods typically center…

Machine Learning · Computer Science 2026-02-19 Guanning Zeng , Zhaoyi Zhou , Daman Arora , Andrea Zanette

We address the challenging problem of deep representation learning--the efficient adaption of a pre-trained deep network to different tasks. Specifically, we propose to explore gradient-based features. These features are gradients of the…

Machine Learning · Computer Science 2020-04-14 Fangzhou Mu , Yingyu Liang , Yin Li

In this paper, a Gauss-Newton Temporal Difference (GNTD) learning method is proposed to solve the Q-learning problem with nonlinear function approximation. In each iteration, our method takes one Gauss-Newton (GN) step to optimize a variant…

Optimization and Control · Mathematics 2024-04-02 Zhifa Ke , Junyu Zhang , Zaiwen Wen

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Neural and Evolutionary Computing · Computer Science 2008-03-26 Michael Fairbank

Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertainty quantification, robustness to noise, resistance to overfitting, and more. The variational…

Machine Learning · Computer Science 2026-05-22 Minyoung Kim

The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD…

Machine Learning · Computer Science 2021-03-16 Deniz Oktay , Nick McGreivy , Joshua Aduol , Alex Beatson , Ryan P. Adams

Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks, even with limited data records. Gradient-based…

Machine Learning · Computer Science 2026-04-16 Yilang Zhang , Abraham Jaeger Mountain , Bingcong Li , Georgios B. Giannakis

Sample inefficiency is a long-lasting challenge in deep reinforcement learning (DRL). Despite dramatic improvements have been made, the problem is far from being solved and is especially challenging in environments with sparse or delayed…

Machine Learning · Computer Science 2025-06-17 Federico Malato , Ville Hautamaki

In this paper, we provide a new algorithm for the problem of prediction in Reinforcement Learning, \emph{i.e.}, estimating the Value Function of a Markov Reward Process (MRP) using the linear function approximation architecture, with memory…

Systems and Control · Computer Science 2016-09-30 Ajin George Joseph , Shalabh Bhatnagar

Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we…

Machine Learning · Computer Science 2019-02-26 Guoqiang Zhang , Kenta Niwa , W. Bastiaan Kleijn