Name
Abstract | ||
|---|---|---|
The design of the control mechanisms for the agents in modern video games is one of the main tasks involved in the game design process. Designing controllers grows in complexity as either the number of different game agents or the number of possible actions increase. An alternative mechanism to hard-coding agent controllers is the use of learning techniques. This paper introduces two new variants of a hybrid algorithm, named WEREWoLF and WERESARSA, that combine evolutionary techniques with reinforcement learning. Both new algorithms allow a group of different reinforcement learning controllers to be recombined in an iterative process that uses both evolution and learning. These new algorithms have been tested against different instances of predefined controllers on a one-on-one combat simulator, with underlying game mechanics similar to classic arcade games of this kind. The results have been compared with other reinforcement learning controllers, showing that WEREWoLF outperforms the other algorithms for a series of different learning conditions. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/CIG.2012.6374156 | Computational Intelligence and Games |
Keywords | Field | DocType |
computer games,control system synthesis,evolutionary computation,iterative methods,learning (artificial intelligence),learning systems,software agents,WERESARSA,WEREWoLF,agent control mechanism design,agent controller hard-coding,arcade game,combat game controller evolution,evolutionary technique,game agent,game design,game mechanics,hybrid algorithm,iterative process,learning condition,learning technique,one-on-one combat simulator,reinforcement learning controller,video game | Hybrid algorithm,Iterative and incremental development,Evolutionary robotics,Game mechanics,Simulation,Computer science,Evolutionary computation,Game design,Artificial intelligence,Machine learning,Learning classifier system,Reinforcement learning | Conference |
ISBN | Citations | PageRank |
978-1-4673-1192-2 | 8 | 0.67 |
References | Authors | |
9 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Luis Peña | 1 | 18 | 3.19 |
| Sascha Ossowski | 2 | 1646 | 158.02 |
| José María Peña | 3 | 118 | 10.30 |
| Simon M. Lucas | 4 | 1660 | 137.66 |