18214528. COMPUTER-READABLE RECORDING MEDIUM STORING MULTI-AGENT REINFORCEMENT LEARNING PROGRAM, INFORMATION PROCESSING APPARATUS, AND MULTI-AGENT REINFORCEMENT LEARNING METHOD simplified abstract (Fujitsu Limited)
Contents
- 1 COMPUTER-READABLE RECORDING MEDIUM STORING MULTI-AGENT REINFORCEMENT LEARNING PROGRAM, INFORMATION PROCESSING APPARATUS, AND MULTI-AGENT REINFORCEMENT LEARNING METHOD
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 COMPUTER-READABLE RECORDING MEDIUM STORING MULTI-AGENT REINFORCEMENT LEARNING PROGRAM, INFORMATION PROCESSING APPARATUS, AND MULTI-AGENT REINFORCEMENT LEARNING METHOD - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
COMPUTER-READABLE RECORDING MEDIUM STORING MULTI-AGENT REINFORCEMENT LEARNING PROGRAM, INFORMATION PROCESSING APPARATUS, AND MULTI-AGENT REINFORCEMENT LEARNING METHOD
Organization Name
Inventor(s)
Yoshihiro Okawa of Yokohama (JP)
Natsuki Ishikawa of Yamato (JP)
COMPUTER-READABLE RECORDING MEDIUM STORING MULTI-AGENT REINFORCEMENT LEARNING PROGRAM, INFORMATION PROCESSING APPARATUS, AND MULTI-AGENT REINFORCEMENT LEARNING METHOD - A simplified explanation of the abstract
This abstract first appeared for US patent application 18214528 titled 'COMPUTER-READABLE RECORDING MEDIUM STORING MULTI-AGENT REINFORCEMENT LEARNING PROGRAM, INFORMATION PROCESSING APPARATUS, AND MULTI-AGENT REINFORCEMENT LEARNING METHOD
Simplified Explanation
The patent application abstract describes a process that involves updating policy parameters of agents in a specific order to influence constraints specific to each agent and system-wide constraints.
- The process involves obtaining a degree of influence on constraints for each agent based on a predetermined update order.
- The updated policy parameter of one agent can affect the degree of influence on constraints for other agents in the update order.
- If the update width of a policy parameter falls within certain ranges determined by the degree of influence on specific and system-wide constraints, the parameter is updated accordingly.
- The updated policy parameter of one agent can also affect the system-wide constraints for other agents in the update order.
Potential Applications
This technology could be applied in multi-agent systems, optimization algorithms, and distributed control systems.
Problems Solved
This technology helps in efficiently updating policy parameters of agents in a distributed system while considering both individual and system-wide constraints.
Benefits
The process allows for coordinated updates of policy parameters in a distributed system, leading to improved overall performance and coordination among agents.
Potential Commercial Applications
- Distributed control systems optimization
- Multi-agent system coordination algorithms
Possible Prior Art
There may be prior art related to distributed optimization algorithms in multi-agent systems or control systems with shared constraints.
Unanswered Questions
How does this process handle conflicting constraints between agents?
The abstract does not specify how conflicting constraints are resolved when updating policy parameters in a multi-agent system.
What computational resources are required to implement this process effectively?
The abstract does not mention the computational resources needed to execute the described process in a real-world application.
Original Abstract Submitted
A process includes obtaining, according to a predetermined update order of a policy parameter of each agent, a degree of influence on a constraint specific to a first agent and a degree of influence on a system-wide constraint in which a degree of influence by an updated policy parameter of a second agent previous to the first agent in the update order is shared, and in a case where an update width of the policy parameter of the first agent exists in both ranges respectively determined depending on the degree of influence on the constraint specific to the first agent and the degree of influence on the system-wide constraint, updating the policy parameter of the first agent and causing the degree of influence on the system-wide constraints by the updated policy parameter to be shared with a third agent next to the first agent in the update order.
