Execution errors enable the evolution of fairness in the ultimatum game
The goal of designing autonomous and successful agents is often attempted by providing mechanisms to choose actions that maximise some reward function. When agents interact with a static environment, the provided reward functions are well-defined and the implementation of traditional learning algori...
| Autor principal: | |
|---|---|
| Outros Autores: | , , |
| Formato: | conferencePaper |
| Idioma: | eng |
| Publicado em: |
2016
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/1822/47899 |
| País: | Portugal |
| Oai: | oai:repositorium.sdum.uminho.pt:1822/47899 |