English
Related papers

Related papers: Scalable Real-Time Recurrent Learning Using Column…

200 papers

During inference, Recurrent Neural Networks (RNNs) scale constant in both FLOPs and GPU memory with increasing context length, as they compress all prior tokens into a fixed-size memory. In contrast, transformers scale linearly in FLOPs…

Machine Learning · Computer Science 2025-05-26 Francois Chaubard , Mykel Kochenderfer

In this work, we introduce Reinforcement Pre-Training (RPT) as a new scaling paradigm for large language models and reinforcement learning (RL). Specifically, we reframe next-token prediction as a reasoning task trained using RL, where it…

Computation and Language · Computer Science 2025-06-10 Qingxiu Dong , Li Dong , Yao Tang , Tianzhu Ye , Yutao Sun , Zhifang Sui , Furu Wei

State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent Neural Network (RNN), which updates the internal state using…

Machine Learning · Computer Science 2021-02-03 Matthew Schlegel , Andrew Jacobsen , Zaheer Abbas , Andrew Patterson , Adam White , Martha White

We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without…

Robotics · Computer Science 2026-05-19 Julian Lemmel , Felix Resch , Mónika Farsang , Ramin Hasani , Daniela Rus , Radu Grosu

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

Machine Learning · Computer Science 2017-01-11 Tanmay Shankar , Santosha K. Dwivedy , Prithwijit Guha

The design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem. To overcome this, we propose a novel RNN…

Machine Learning · Computer Science 2021-08-19 T. Konstantin Rusch , Siddhartha Mishra

Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has…

Machine Learning · Statistics 2021-11-08 Kentaro Ohno , Atsutoshi Kumagai

Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robotic problems with a…

Robotics · Computer Science 2022-01-26 Taisuke Kobayashi

Recurrent Neural Network (RNN) has been widely applied for sequence modeling. In RNN, the hidden states at current step are full connected to those at previous step, thus the influence from less related features at previous step may…

Computation and Language · Computer Science 2017-05-04 Danhao Zhu , Si Shen , Xin-Yu Dai , Jiajun Chen

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation…

Machine Learning · Computer Science 2019-12-02 Julia El Zini , Yara Rizk , Mariette Awad

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Machine Learning · Computer Science 2025-10-06 Aleksei Arzhantsev , Otmane Sakhi , Flavian Vasile

Systems characterized by evolving interactions, prevalent in social, financial, and biological domains, are effectively modeled as continuous-time dynamic graphs (CTDGs). To manage the scale and complexity of these graph datasets, machine…

Machine Learning · Computer Science 2024-12-31 João Bravo , Jacopo Bono , Pedro Saleiro , Hugo Ferreira , Pedro Bizarro

Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagation through time, which entails unfolding the network over…

Neural and Evolutionary Computing · Computer Science 2019-08-13 Alexander Ororbia , Ankur Mali , C. Lee Giles , Daniel Kifer

Neuromorphic hardware strives to emulate brain-like neural networks and thus holds the promise for scalable, low-power information processing on temporal data streams. Yet, to solve real-world problems, these networks need to be trained.…

Neural and Evolutionary Computing · Computer Science 2020-10-23 Friedemann Zenke , Emre O. Neftci

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…

Neural and Evolutionary Computing · Computer Science 2016-06-13 Audrūnas Gruslys , Remi Munos , Ivo Danihelka , Marc Lanctot , Alex Graves

Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high…

Neural and Evolutionary Computing · Computer Science 2023-08-08 Qingyan Meng , Mingqing Xiao , Shen Yan , Yisen Wang , Zhouchen Lin , Zhi-Quan Luo

A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT…

Artificial Intelligence · Computer Science 2017-11-08 Nan Rosemary Ke , Anirudh Goyal , Olexa Bilaniuk , Jonathan Binas , Laurent Charlin , Chris Pal , Yoshua Bengio

Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in deep recurrent architectures with sparse connectivity remains a major challenge. In this…

Neural and Evolutionary Computing · Computer Science 2026-05-04 Bo Tang , Weiwei Xie

We present Gradient Boosting Reinforcement Learning (GBRL), a framework that adapts the strengths of gradient boosting trees (GBT) to reinforcement learning (RL) tasks. While neural networks (NNs) have become the de facto choice for RL,…

Machine Learning · Computer Science 2025-10-21 Benjamin Fuhrer , Chen Tessler , Gal Dalal

The ability to process time-series at low energy cost is critical for many applications. Recurrent neural network, which can perform such tasks, are computationally expensive when implementing in software on conventional computers. Here we…

Disordered Systems and Neural Networks · Physics 2025-03-05 Erwan Plouet , Dédalo Sanz-Hernández , Aymeric Vecchiola , Julie Grollier , Frank Mizrahi