English
Related papers

Related papers: First Experiments with PowerPlay

200 papers

Replay in the brain has been viewed as rehearsal, or, more recently, as sampling from a transition model. Here, we propose a new hypothesis: that replay is able to implement a form of compositional computation where entities are assembled…

Neurons and Cognition · Quantitative Biology 2022-12-21 Zeb Kurth-Nelson , Timothy Behrens , Greg Wayne , Kevin Miller , Lennart Luettgau , Ray Dolan , Yunzhe Liu , Philipp Schwartenbeck

Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often plateau quickly. A central failure mode is that the loop…

Machine Learning · Computer Science 2026-05-19 Wei Liu , Siya Qi , Yali Du , Yulan He

This work introduces a growable and modular neural network architecture that naturally avoids catastrophic forgetting and interference in continual reinforcement learning. The structure of each module allows the selective combination of…

Machine Learning · Computer Science 2025-06-19 Mikel Malagón , Josu Ceberio , Jose A. Lozano

Humans learn to play video games significantly faster than the state-of-the-art reinforcement learning (RL) algorithms. People seem to build simple models that are easy to learn to support planning and strategic exploration. Inspired by…

Artificial Intelligence · Computer Science 2018-11-27 Ramtin Keramati , Jay Whang , Patrick Cho , Emma Brunskill

Solving Inductive Logic Programming (ILP) problems with neural networks is a key challenge in Neural-Symbolic Ar- tificial Intelligence (AI). While most research has focused on designing novel network architectures for individual prob-…

Artificial Intelligence · Computer Science 2025-11-18 Bowen He , Xiaoan Xu , Alper Kamil Bozkurt , Vahid Tarokh , Juncheng Dong

Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms presently require millions of training steps in order to…

Machine Learning · Computer Science 2018-01-09 Benjamin Spector , Serge Belongie

Deep Reinforcement Learning (RL) can yield capable agents and control policies in several domains but is commonly plagued by prohibitively long training times. Additionally, in the case of continuous control problems, the applicability of…

Machine Learning · Computer Science 2024-11-20 Jonas Eschmann , Dario Albani , Giuseppe Loianno

Vanilla spiking neurons in Spiking Neural Networks (SNNs) use charge-fire-reset neuronal dynamics, which can only be simulated serially and can hardly learn long-time dependencies. We find that when removing reset, the neuronal dynamics can…

Neural and Evolutionary Computing · Computer Science 2024-01-10 Wei Fang , Zhaofei Yu , Zhaokun Zhou , Ding Chen , Yanqi Chen , Zhengyu Ma , Timothée Masquelier , Yonghong Tian

Memory replay may be key to learning in biological brains, which manage to learn new tasks continually without catastrophically interfering with previous knowledge. On the other hand, artificial neural networks suffer from catastrophic…

Machine Learning · Computer Science 2022-01-06 Haitz Sáez de Ocáriz Borde

Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal approximation ability and robustness to adversarial examples under appropriate conditions. However, SMNNs present some…

Machine Learning · Computer Science 2024-03-22 Eduardo Paluzo-Hidalgo , Miguel A. Gutiérrez-Naranjo , Rocio Gonzalez-Diaz

Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the prospect of growing a strong LLM out of a weak one without the need…

Machine Learning · Computer Science 2024-06-18 Zixiang Chen , Yihe Deng , Huizhuo Yuan , Kaixuan Ji , Quanquan Gu

Recurrent neural networks (RNNs) trained using Equilibrium Propagation (EP), a biologically plausible training algorithm, have demonstrated strong performance in various tasks such as image classification and reinforcement learning.…

Machine Learning · Computer Science 2025-08-21 Yoshimasa Kubo , Jean Erik Delanois , Maxim Bazhenov

Deep Reinforcement Learning (Deep RL) has had incredible achievements on high dimensional problems, yet its learning process remains unstable even on the simplest tasks. Deep RL uses neural networks as function approximators. These neural…

Machine Learning · Computer Science 2022-10-18 Riccardo Della Vecchia , Alena Shilova , Philippe Preux , Riad Akrour

Reinforcement learning algorithms are used in a wide range of applications, from gaming and robotics to autonomous vehicles. In this paper we describe a set of reinforcement learning-based local weight update rules and their implementation…

Superconductivity · Physics 2025-03-05 M. L. Schneider , E. M. Jué , M. R. Pufall , K. Segall , C. W. Anderson

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems.…

Machine Learning · Computer Science 2022-04-12 Yunbo Wang , Haixu Wu , Jianjin Zhang , Zhifeng Gao , Jianmin Wang , Philip S. Yu , Mingsheng Long

This paper presents a new neural network (NN) paradigm for scalable and generalizable stability analysis of power systems. The paradigm consists of two parts: the neural stability descriptor and the sample-augmented iterative training…

Systems and Control · Electrical Eng. & Systems 2025-10-30 Tong Han , Yan Xu , Rui Zhang

Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the…

Machine Learning · Computer Science 2018-06-04 Shagun Sodhani , Vardaan Pahuja

It is widely accepted that the complex dynamics characteristic of recurrent neural circuits contributes in a fundamental manner to brain function. Progress has been slow in understanding and exploiting the computational power of recurrent…

Chaotic Dynamics · Physics 2013-07-18 Rodrigo Laje , Dean V. Buonomano

Deep neural networks (DNNs) are nowadays ubiquitous in many domains such as computer vision. However, due to their high latency, the deployment of DNNs hinges on the development of compression techniques such as quantization which consists…

Computer Vision and Pattern Recognition · Computer Science 2023-01-25 Edouard Yvinec , Arnaud Dapogny , Matthieu Cord , Kevin Bailly

Neural plasticity is an important functionality of human brain, in which number of neurons and synapses can shrink or expand in response to stimuli throughout the span of life. We model this dynamic learning process as an $L_0$-norm…

Neural and Evolutionary Computing · Computer Science 2021-05-04 Yang Li , Shihao Ji