Name
Abstract | ||
|---|---|---|
Abstractó This paper presents a method for obtaining optimal policies which allow for action planning and optimal control in non-communicating multiagent system. In this system homogeneous agents have the same structure and domain but act and are situated differently in the world. Lack of information about each other’s internal state and observation inputs may lead to non-desirable prediction in planning and control, since they may not be able to predict the world change. To cope with missing knowledge, agents simulate each other’s behavior as part of environment dynamic and build their own policy based on the local data from the simulation episodes. Reinforcement learning method is applied to derive the policy of future actions, where agents compute and update the result repeatedly towards the goal. The Monte Carlo approach is used in solving the reinforcement problem from simulated experiences. Since each agent learns to adapt it’s policy to environment changes, the global picture is supposed to appear as multiagent coordination. Multiple vehicles domain, where there is no communication among the vehicles and sensing of vehicle is limited, is considered under simulation model. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/RAMECH.2004.1437994 | RAM |
Keywords | Field | DocType |
simulation experiment,reinforcement learning,simulation model,dynamic system,intelligent control,monte carlo,optimal control | Situated,Intelligent control,Monte Carlo method,Optimal control,Control engineering,Multi-agent system,Artificial intelligence,Action planning,Engineering,Reinforcement,Reinforcement learning | Conference |
Volume | ISBN | Citations |
2 | 0-7803-8645-0 | 1 |
PageRank | References | Authors |
0.48 | 5 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Damba Ariuna | 1 | 1 | 1.16 |
| Shigeyoshi Watanabe | 2 | 15 | 7.42 |