Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

State Space Representation

State Space Representation

The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...

Associative Learning

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...

Introduction to Learning

Introduction to Learning

Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...

State Space to Transfer Function

State Space to Transfer Function

The conversion of state-space representation to a transfer function is a fundamental process in system analysis. It provides a method for transitioning from a time-domain description to a frequency-domain representation, which is crucial for simplifying the analysis and design of control systems.
The transformation process begins with the state-space representation, characterized by the state equation and the output equation. These equations are typically represented as:

Traits and States

Traits and States

Personality traits represent consistent patterns in behavior, thoughts, and emotions, reflecting an individual's tendencies across various situations. For example, extraversion, a well-known trait, manifests in individuals as talkative, energetic, and enthusiastic behaviors. These traits are stable over time, offering a reliable framework for predicting how people might act in different contexts. However, they do not define every moment of an individual's life. In contrast to traits,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Yomix: an interactive tool for the exploration of low-dimensional embeddings in omics data.

Bioinformatics (Oxford, England)·2026

Same author

Quality Diversity under Sparse Interaction and Sparse Reward: Application to Grasping in Robotics.

Evolutionary computation·2025

Same author

Discovering and Exploiting Sparse Rewards in a Learned Behavior Space.

Evolutionary computation·2023

Same author

Building an Affordances Map With Interactive Perception.

Frontiers in neurorobotics·2022

Same author

Editorial: Evolvability, Environments, Embodiment & Emergence in Robotics.

Frontiers in robotics and AI·2021

Same author

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities.

Artificial life·2020

Same journal

Passive wheels on legged robots: a survey.

Frontiers in robotics and AI·2026

Same journal

Politeness cannot make up for robots' errors.

Frontiers in robotics and AI·2026

Same journal

Workers expect basic social skills but limited autonomy from future robots - a qualitative interview study and taxonomy for robot social skills.

Frontiers in robotics and AI·2026

Same journal

Human-robot interaction in sustainable hospitality: how robot type shapes customer emotions, green perceptions, and service loyalty.

Frontiers in robotics and AI·2026

Same journal

Dynamic variance-aware federated tuning for efficient autonomous vehicle perception under non-IID settings.

Frontiers in robotics and AI·2026

Same journal

Editorial: Synergizing large language models and computational intelligence for advanced robotic systems.

Frontiers in robotics and AI·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 1, 2025

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Exploratory State Representation Learning.

Astrid Merckling¹, Nicolas Perrin-Gilbert¹, Alex Coninx¹

¹Sorbonne Université, CNRS, Institut des Systèmes Intelligents et de Robotique, ISIR, Paris, France.

Frontiers in Robotics and AI

|March 3, 2022

Summary

This summary is machine-generated.

We introduce Exploratory State Representation Learning (XSRL) to improve reinforcement learning (RL). XSRL enhances exploration and state representation learning simultaneously, accelerating task completion in complex environments.

Keywords:

deep reinforcement learning exploration pretraining state representation learning unsupervised learning

More Related Videos

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Related Experiment Videos

Last Updated: Oct 1, 2025

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Area of Science:

Artificial Intelligence
Machine Learning
Robotics

Background:

Reinforcement learning (RL) complexity increases without compact state representations.
State representation learning (SRL) requires diverse transitions, often hindered by difficult exploration, especially in reward-free environments.

Purpose of the Study:

To address challenges in exploration and SRL simultaneously.
To propose a novel approach, Exploratory State Representation Learning (XSRL), for efficient learning in RL.

Main Methods:

XSRL jointly learns compact state representations and a state transition estimator.
It removes unexploitable information from representations using the estimator.
A discovery policy is optimized using an inverse model's prediction error plus a k-step learning progress bonus.

Main Results:

XSRL demonstrates efficient exploration in challenging, image-based environments.
The learned state representations significantly accelerate subsequent RL tasks.
The approach effectively guides policies towards complex, informative transitions.

Conclusions:

XSRL offers a unified solution for parallel exploration and state representation learning.
This method enhances RL agent performance in complex scenarios.
XSRL facilitates faster and more effective learning by optimizing discovery policies.