English
Related papers

Related papers: Adaptive Tree Backup Algorithms for Temporal-Diffe…

200 papers

Reinforcement learning (RL) has gained increasing interest since the demonstration it was able to reach human performance on video game benchmarks using deep Q-learning (DQN). The current consensus for training neural networks on such…

Machine Learning · Computer Science 2021-06-22 Luong Ha , Nguyen , James-A. Goulet

To maintain the accuracy of supervised learning models in the presence of evolving data streams, we provide temporally-biased sampling schemes that weight recent data most heavily, with inclusion probabilities for a given data item decaying…

Databases · Computer Science 2018-01-31 Brian Hentschel , Peter J. Haas , Yuanyuan Tian

Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that the value update introduces bias when predicting the TD…

Machine Learning · Computer Science 2021-10-29 Litian Liang , Yaosheng Xu , Stephen McAleer , Dailin Hu , Alexander Ihler , Pieter Abbeel , Roy Fox

Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despite its empirical success, the learnability of TTA under non-stationary streams remains…

Machine Learning · Computer Science 2026-05-28 Zhi Zhou , Ming Yang , Shi-Yu Tian , Kun-Yang Yu , Lan-Zhe Guo , Yu-Feng Li

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

Data augmentation is known to contribute significantly to the robustness of machine learning models. In most instances, data augmentation is utilized during the training phase. Test-Time Augmentation (TTA) is a technique that instead…

Machine Learning · Statistics 2024-09-20 Masanari Kimura , Howard Bondell

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

We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Kambiz Azarian , Debasmit Das , Hyojin Park , Fatih Porikli

Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC)…

Machine Learning · Statistics 2026-02-27 Aayush Mishra , Šimon Kucharský , Paul-Christian Bürkner

We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling. APG samplers construct high-dimensional proposals by iterating over updates to…

Machine Learning · Statistics 2020-07-13 Hao Wu , Heiko Zimmermann , Eli Sennesh , Tuan Anh Le , Jan-Willem van de Meent

The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD({\lambda}) to data efficient least squares methods. Least square methods make the best use of available data directly…

Artificial Intelligence · Computer Science 2017-03-13 Yangchen Pan , Adam White , Martha White

Graph-based learning excels at capturing interaction patterns in diverse domains like recommendation, fraud detection, and particle physics. However, its performance often degrades under distribution shifts, especially those altering…

Machine Learning · Computer Science 2026-05-12 Hans Hao-Hsun Hsu , Shikun Liu , Han Zhao , Pan Li

Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchronized forward and…

Machine Learning · Computer Science 2026-03-03 Marc Gong Bacvanski , Liu Ziyin , Tomaso Poggio

Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online…

Machine Learning · Computer Science 2026-02-24 Sarthak Kumar Maharana , Akshay Mehra , Bhavya Ramakrishna , Yunhui Guo , Guan-Ming Su

The main challenge in domain generalization (DG) is to handle the distribution shift problem that lies between the training and test data. Recent studies suggest that test-time training (TTT), which adapts the learned model with test data,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Liang Chen , Yong Zhang , Yibing Song , Ying Shan , Lingqiao Liu

Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algorithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and…

Machine Learning · Computer Science 2024-09-04 Mark Bedaywi , Amin Rakhsha , Amir-massoud Farahmand

To maintain the accuracy of supervised learning models in the presence of evolving data streams, we provide temporally-biased sampling schemes that weight recent data most heavily, with inclusion probabilities for a given data item decaying…

Databases · Computer Science 2019-06-14 Brian Hentschel , Peter J. Haas , Yuanyuan Tian

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

Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning…

Machine Learning · Computer Science 2019-01-04 Ahmed Touati , Pierre-Luc Bacon , Doina Precup , Pascal Vincent

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