Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Reinforcement01:23

Reinforcement

615
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:
615
Reinforcement Schedules01:24

Reinforcement Schedules

330
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,...
330
Observational Learning01:12

Observational Learning

641
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...
641
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.3K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.3K
Purposive Learning01:22

Purposive Learning

302
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
302
Associative Learning01:27

Associative Learning

882
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...
882

You might also read

Related Articles

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

Sort by
Same author

Efficacy and safety of anti-PD-1-based therapies in advanced melanoma across acral and mucosal subtypes: a nationwide retrospective cohort study.

Cancer immunology, immunotherapy : CII·2026
Same author

Corrigendum to "Er-Chen decoction alleviates spermatogenic dysfunction in obese mice by tuning the SIRT1/p53 axis" [J. Ethnopharmacol. 356 (2026) 120758].

Journal of ethnopharmacology·2026
Same author

Risk Factors and Comparative Safety of Anti-PD-1 Combination Therapies in Advanced Melanoma: A Nationwide Real-World Cohort Study From China.

Cancer medicine·2026
Same author

Time of day alters olfactory bulb immune state with ramifications for intranasal inflammatory challenge.

Cell reports·2026
Same author

Energy-efficient path planning for Robotic Bulkhead Inspection using Residual-Enhanced UKF and Hierarchical MPC.

PloS one·2026
Same author

Long-term survival after ALK-TKI resistance through immunotherapy combined with chemotherapy in ALK-positive non-small cell lung cancer: a case report.

Frontiers in oncology·2025

Related Experiment Video

Updated: Nov 23, 2025

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

9.0K

Modular deep reinforcement learning from reward and punishment for robot navigation.

Jiexin Wang1, Stefan Elfwing2, Eiji Uchibe1

  • 1Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seikacho, Soraku-gun, Kyoto 619-0288, Japan.

Neural Networks : the Official Journal of the International Neural Network Society
|December 31, 2020
PubMed
Summary

This study introduces novel methods for modular reinforcement learning (RL) by dynamically weighting reward and punishment signals. The approach enhances learning efficiency and safety in navigation tasks, outperforming traditional RL techniques.

Keywords:
Deep reinforcement learningMax painMaze solvingModular reinforcement learningRobot navigation

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.6K
An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice
08:59

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

Published on: March 3, 2023

2.4K

Related Experiment Videos

Last Updated: Nov 23, 2025

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

9.0K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.6K
An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice
08:59

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

Published on: March 3, 2023

2.4K

Area of Science:

  • Neuroscience and Artificial Intelligence
  • Robotics and Machine Learning

Background:

  • Modular Reinforcement Learning (RL) decomposes complex tasks into sub-goals, mirroring animal learning.
  • Existing dichotomy-based RL methods (MaxPain, Deep MaxPain) use separate reward and punishment systems but rely on manual weight tuning.
  • Manual weighting limits the effective utilization of learned RL modules.

Purpose of the Study:

  • To address the limitations of manual weight determination in dichotomy-based RL.
  • To propose a state-value dependent weighting scheme for automatic tuning of reward and punishment signals.
  • To improve safety and learning efficiency in modular RL tasks, particularly in navigation.

Main Methods:

  • Investigated signal scaling of reward and punishment concerning the discounting factor gamma.
  • Proposed a weak constraint for signaling design and a state-value dependent weighting scheme (hard-max and softmax) based on Boltzmann distribution analysis.
  • Developed a sensor fusion network combining lidar and monocular camera data for enhanced environmental perception.

Main Results:

  • The proposed automatic weighting scheme effectively tuned mixing weights, improving module utilization.
  • Sensor fusion network demonstrated superior performance compared to single-sensor approaches in simulations and real-world robot experiments.
  • The methods showed significant improvements in safety and learning efficiency for maze-solving navigation tasks.

Conclusions:

  • Dynamically weighting reward and punishment signals based on state-value is crucial for optimizing modular RL.
  • Sensor fusion enhances robustness and performance in robotic navigation tasks.
  • The developed approach offers a more efficient and safer alternative to conventional RL methods.