Name
Title | ||
|---|---|---|
Learning action descriptions of opponent behaviour in the robocup 2D simulation environment |
Abstract | ||
|---|---|---|
The Robocup 2D simulation competition [13] proposes a dynamic environment where two opponent teams are confronted in a simplified soccer game. All major teams use a fixed algorithm to control its players. An unexpected opponent strategy, not previously considered by the developers, might result in winning all matches. To improve this we use ILP to learn action descriptions of opponent players; for learning on dynamic domains, we have to deal with the frame problem. The induced descriptions can be used to plan for desired field states. To show this we start with a simplified scenario where we learn the behaviour of a goalkeeper based on the actions of a shooter player. This description is used to plan for states where a goal can be scored. This result can directly be extended to a multiplayer environment. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-21295-6_14 | ILP |
Keywords | Field | DocType |
fixed algorithm,dynamic domain,action description,opponent player,multiplayer environment,opponent team,dynamic environment,frame problem,unexpected opponent strategy,simulation environment,opponent behaviour,field state | Computer science,Artificial intelligence,Non-monotonic logic,Adversary,Frame problem,Machine learning | Conference |
Volume | ISSN | Citations |
6489 | 0302-9743 | 2 |
PageRank | References | Authors |
0.36 | 9 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| A. Illobre | 1 | 2 | 0.36 |
| J. Gonzalez | 2 | 2 | 0.36 |
| R. Otero | 3 | 2 | 0.36 |
| José Santos | 4 | 97 | 14.77 |