Loading...
Please wait, while we are loading the content...
Similar Documents
Evolving Drivers for TORCS using On-Line Neuroevolution
| Content Provider | Semantic Scholar |
|---|---|
| Author | Cardamone, Luigi Loiacono, Daniele Lanzi, Pier Luca |
| Copyright Year | 2009 |
| Abstract | We applied on-line neuroevolution to evolve non-player characters for The Open Racing Car Simulator. While previous approaches allowed on-line learning with performance improvements during each generation, our approach enables a finer grained on-line learning with performance improvements within each lap. We tested our approach on three tracks using two methods of online neuroevolution (NEAT and rtNEAT) combined with four evaluation strategies (ε-Greedy, ε-Greedy-Improved, Softmax, and Interval-based) taken from the literature. We compared the eight resulting configurations on several driving tasks involving (i) the learning of a driving behavior for a specific track, (ii) its adaptation to a new track, and (iii) the generalization capability to unknown tracks. The results we present show that our approach can successfully evolve drivers from scratch and can also be used to transfer evolved knowledge to other tracks. Overall, our results suggest that the approach performs significantly better when coupled with on-line NEAT and also indicate that ε-Greedy-Improved, Softmax are generally better than the other evaluation strategies. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.illigal.uiuc.edu/pub/papers/IlliGALs/2009008.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
