Related Experiment Video
Updated: Sep 24, 2025
08:18
WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control
Published on: August 15, 2020
5.1K
Event-triggered integral reinforcement learning for nonzero-sum games with asymmetric input saturation.
Shan Xue1, Biao Luo2, Derong Liu3
1School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China; Peng Cheng Laboratory, Shenzhen 518000, China.
Summary
This study introduces an event-triggered integral reinforcement learning (IRL) algorithm for complex control problems. The new method efficiently learns optimal strategies, ensuring system stability and avoiding Zeno behavior in control systems.
Area of Science:
- Control Theory
- Artificial Intelligence
- Game Theory
Background:
- Nonzero-sum games present complex control challenges.
- Asymmetric input saturation complicates system dynamics.
- Integral Reinforcement Learning (IRL) offers a data-driven approach to control.
Purpose of the Study:
- Develop an event-triggered IRL algorithm for nonzero-sum games.
- Address asymmetric input saturation in control systems.
- Ensure system stability and prevent Zeno behavior.
Main Methods:
- Designed a novel non-quadratic value function for each player.
- Derived coupled Hamilton-Jacobi equations using IRL.
- Implemented an adaptive dynamic programming scheme with a single critic neural network (NN).
- Utilized experience replay with gradient descent for NN weight tuning.
Main Results:
- Successfully developed an event-triggered IRL algorithm.
- Demonstrated the elimination of Zeno behavior.
- Proved the stability of the closed-loop system.
- Validated the algorithm's effectiveness through simulations.
Conclusions:
- The proposed event-triggered IRL algorithm is effective for nonzero-sum games with asymmetric input saturation.
- The method ensures system stability and avoids Zeno behavior.
- Adaptive dynamic programming with experience replay provides an efficient learning scheme.
Related Concept Videos
01:24Reinforcement Schedules
244
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,...
Once a behavior is learned,...
244
01:59Solution Equilibrium and Saturation
19.7K
Imagine adding a small amount of sugar to a glass of water, stirring until all the sugar has dissolved, and then adding a bit more. You can repeat this process until the sugar concentration of the solution reaches its natural limit, a limit determined primarily by the relative strengths of the solute-solute, solute-solvent, and solvent-solvent attractive forces. You can be certain that you have reached this limit because, no matter how long you stir the solution, undissolved sugar remains. The...
19.7K
01:13Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
130
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
130
01:23Reinforcement
360
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:
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
360
01:22Multi-input and Multi-variable systems
172
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
172
01:28Integration of Synaptic Events
2.3K
Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...
2.3K