Title | ||
---|---|---|
An Action Selection Method Based on Estimation of Other's Intention in Time-Varying Multi-agent Environments. |
Abstract | ||
---|---|---|
An action selection method based on the estimation of other's intention is proposed to treat with time-varying multi-agent environments. Firstly, the estimation level of other's intention is stratified as active, passive and thoughtful levels. Secondly, three estimation levels are formulated by a policy estimation method. Thirdly, a new action selection method by switching three estimation levels is proposed to cope with time-varying environments. Fourthly, the estimation methods of other's intention are applied to the Q-learning method. Finally, through computer simulations using pursuit problems, the performance of the estimation methods are investigated. As a result, it is shown that the proposed method can select the appropriate estimation level in time-varying environments. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-24965-5_9 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Multi-agent system,Reinforcement learning,Intention estimation,Action selection,Pursuit problem | Computer science,Multi-agent system,Artificial intelligence,Action selection,Machine learning,Reinforcement learning | Conference |
Volume | ISSN | Citations |
7064 | 0302-9743 | 1 |
PageRank | References | Authors |
0.43 | 2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kunikazu Kobayashi | 1 | 173 | 21.96 |
Ryu Kanehira | 2 | 1 | 0.43 |
Takashi Kuremoto | 3 | 196 | 27.73 |
Masanao Obayashi | 4 | 198 | 26.10 |