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

Reinforcement Schedules

Reinforcement Schedules

Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...

Reinforcement

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

You might also read

Related Articles

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

Sort by

Same author

LSWM: A Long-Short History World Model for Bipedal Locomotion via Reinforcement Learning.

Biomimetics (Basel, Switzerland)·2026

Same author

Adaptive Graph Learning with Multimodal Fusion for Emotion Recognition in Conversation.

Biomimetics (Basel, Switzerland)·2025

Same author

Multi-Humanoid Robot Arm Motion Imitation and Collaboration Based on Improved Retargeting.

Biomimetics (Basel, Switzerland)·2025

Same author

Exploiting Arch-like Foot Structure for Knee-Extended Walking in Bipedal Robots.

Biomimetics (Basel, Switzerland)·2025

Same author

A Multi-Agent Reinforcement Learning Method for Omnidirectional Walking of Bipedal Robots.

Biomimetics (Basel, Switzerland)·2023

Same author

Capecitabine maintenance therapy in metastatic colorectal cancer patients with no evidence of disease: CAMCO trial.

Future oncology (London, England)·2023

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

A Two-Stage Reinforcement Learning Framework for Humanoid Robot Sitting and Standing-Up.

Xisheng Jiang^1,2,3,4, Shihai Zhao^1,2, Yudi Zhu^1,2,3,4

¹School of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.

Biomimetics (Basel, Switzerland)

|November 26, 2025

Summary

This summary is machine-generated.

Humanoid robots can now autonomously sit and stand using a novel two-stage reinforcement learning (RL) framework. This method enhances robot stability and smoothness for practical daily-life applications.

Keywords:

bi-level optimization humanoid robots reinforcement learning two-stage

More Related Videos

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Related Experiment Videos

Last Updated: Jan 10, 2026

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Area of Science:

Robotics
Artificial Intelligence

Background:

Humanoid robots require autonomous sitting and standing for practical applications, but traditional controllers struggle with complex dynamics and varied scenarios.
Reinforcement Learning (RL) offers potential for motion control but often results in unstable or abrupt movements.

Purpose of the Study:

To develop a robust two-stage reinforcement learning framework for smooth and stable autonomous sitting and standing in humanoid robots.
To overcome the limitations of direct RL training in achieving balanced motion control.

Main Methods:

A two-stage reinforcement learning approach: initial policy training with relaxed constraints, followed by trajectory tracking refinement.
Bi-level optimization for adaptive curriculum learning, dynamically adjusting tracking precision based on error.

Main Results:

Stable execution of autonomous sitting and standing motions on a 1.7 m adult-scale humanoid robot.
Successful demonstration in real-world scenarios involving sitting down and standing up from a chair.

Conclusions:

The proposed two-stage RL framework effectively generates smooth and stable humanoid robot motions for daily tasks.
This approach offers a promising solution for enhancing humanoid robot autonomy and practicality in real-world environments.