English
Related papers

Related papers: Novelty Producing Synaptic Plasticity

200 papers

When users work with AI agents, they form conscious or subconscious expectations of them. Meeting user expectations is crucial for such agents to engage in successful interactions and teaming. However, users may form expectations of an…

Artificial Intelligence · Computer Science 2025-09-26 Akkamahadevi Hanni , Jonathan Montaño , Yu Zhang

We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…

Machine Learning · Computer Science 2025-06-11 Haozhe Ma , Guoji Fu , Zhengding Luo , Jiele Wu , Tze-Yun Leong

Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success in many complex tasks, these algorithms need a large number…

In the domain of machine learning, Neural Memory Networks (NMNs) have recently achieved impressive results in a variety of application areas including visual question answering, trajectory prediction, object tracking, and language…

Neural and Evolutionary Computing · Computer Science 2019-10-15 Tharindu Fernando , Simon Denman , David Ahmedt-Aristizabal , Sridha Sridharan , Kristin Laurens , Patrick Johnston , Clinton Fookes

The ability to flexibly compose previously acquired skills to execute intelligent behaviors is a hallmark of natural intelligence. Such compositional flexibility is often attributed to context-dependent gating mechanisms that determine how…

Optimization and Control · Mathematics 2026-05-18 Francesca Rossi , Veronica Centorrino , Francesco Bullo , Giovanni Russo

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potentially mitigate…

Machine Learning · Computer Science 2024-05-21 Guozheng Ma , Lu Li , Sen Zhang , Zixuan Liu , Zhen Wang , Yixin Chen , Li Shen , Xueqian Wang , Dacheng Tao

A key question in neuroscience is at which level functional meaning emerges from biophysical phenomena. In most vertebrate systems, precise functions are assigned at the level of neural populations, while single-neurons are deemed…

Neurons and Cognition · Quantitative Biology 2017-03-17 Wieland Brendel , Ralph Bourdoukan , Pietro Vertechi , Christian K. Machens , Sophie Denéve

Numerous past works have tackled the problem of task-driven navigation. But, how to effectively explore a new environment to enable a variety of down-stream tasks has received much less attention. In this work, we study how agents can…

Robotics · Computer Science 2019-03-06 Tao Chen , Saurabh Gupta , Abhinav Gupta

One of the main problems of evolutionary algorithms is the convergence of the population to local minima. In this paper, we explore techniques that can avoid this problem by encouraging a diverse behavior of the agents through a shared…

Neural and Evolutionary Computing · Computer Science 2022-08-04 David Herel , Dominika Zogatova , Matej Kripner , Tomas Mikolov

The dynamics of local cortical networks are irregular, but correlated. Dynamic excitatory--inhibitory balance is a plausible mechanism that generates such irregular activity, but it remains unclear how balance is achieved and maintained in…

Neurons and Cognition · Quantitative Biology 2020-04-28 Alan Eric Akil , Robert Rosenbaum , Krešimir Josić

Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Daniel Fried , Ronghang Hu , Volkan Cirik , Anna Rohrbach , Jacob Andreas , Louis-Philippe Morency , Taylor Berg-Kirkpatrick , Kate Saenko , Dan Klein , Trevor Darrell

Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "novelty" of states, transitions, or trajectories with deep…

Machine Learning · Computer Science 2023-05-17 Toru Lin , Allan Jabri

As machine learning models, specifically neural networks, are becoming increasingly popular, there are concerns regarding their trustworthiness, specially in safety-critical applications, e.g. actions of an autonomous vehicle must be safe.…

Machine Learning · Computer Science 2023-12-15 Kshitij Goyal , Sebastijan Dumancic , Hendrik Blockeel

Neural circuits exhibit remarkable computational flexibility, enabling adaptive responses to noisy and ever-changing environmental cues. A fundamental question in neuroscience concerns how a wide range of behaviors can emerge from a…

Statistical Mechanics · Physics 2025-09-18 Giacomo Barzon , Daniel M. Busiello , Giorgio Nicoletti

Many autonomous systems face safety challenges, requiring robust closed-loop control to handle physical limitations and safety constraints. Real-world systems, like autonomous ships, encounter nonlinear dynamics and environmental…

Robotics · Computer Science 2024-04-03 Aksel Vaaler , Svein Jostein Husa , Daniel Menges , Thomas Nakken Larsen , Adil Rasheed

Symbolic regression is a type of discrete optimization problem that involves searching expressions that fit given data points. In many cases, other mathematical constraints about the unknown expression not only provide more information…

Machine Learning · Computer Science 2021-02-16 Li Li , Minjie Fan , Rishabh Singh , Patrick Riley

Reinforcement learning involves agents interacting with an environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the quality of actions that they take, thereby…

Multiagent Systems · Computer Science 2022-02-22 Baicen Xiao , Bhaskar Ramasubramanian , Radha Poovendran

The plasticity of the conduction delay between neurons plays a fundamental role in learning. However, the exact underlying mechanisms in the brain for this modulation is still an open problem. Understanding the precise adjustment of…

Neural and Evolutionary Computing · Computer Science 2020-11-19 Alireza Nadafian , Mohammad Ganjtabesh

Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…

Machine Learning · Computer Science 2016-10-07 William Montgomery , Anurag Ajay , Chelsea Finn , Pieter Abbeel , Sergey Levine

A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, discusses similarities between learning dynamics employed in deep…

Neural and Evolutionary Computing · Computer Science 2020-05-22 Jacques Kaiser , Hesham Mostafa , Emre Neftci