In this paper, we applied online neuroevolution to evolve nonplayer characters for The Open Racing Car Simulator (TORCS). While previous approaches allowed online learning with per...
Luigi Cardamone, Daniele Loiacono, Pier Luca Lanzi
Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11transistor primitive, that we term an automaximizing ...
To cope with large scale, agents are usually organized in a network such that an agent interacts only with its immediate neighbors in the network. Reinforcement learning technique...
The inherent and increasing complexity, heterogeneity and unpredictability of computer networks make the task of managing these systems highly complex. The autonomic computing para...
Romildo Martins da Silva Bezerra, Joberto Sé...
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...