
www.Usenet.com
| <-- __Chronological__ --> | <-- __Thread__ --> |
> > > Is collaboration possible without communication? > > Hi Christian, > > The large mass of multi-agent (reinforcement) learning is about learning > some task with multiple agents, without communicating at all. > Many systems work by 'shared rewards', so that agents will learn to do > their actions in the benefit of the whole system. More sophisticated > approaches use for example 'wonderful life utility' in which the > difference between system+agent1 and system-without-agent1 for example. > Thanks Martijn. The notion of collaboration among agents is somewhat integrated by the designer of such learning system. There may be no explicit and direct communication during run time, but a model of collaborative utility is captured when designing the system and before reinforcement learning takes place , isn't it? cheers, Christian [ comp.ai is moderated. To submit, just post and be patient, or if ] [ that fails mail your article to <[EMAIL PROTECTED]>, and ] [ ask your news administrator to fix the problems with your system. ]
| <-- __Chronological__ --> | <-- __Thread__ --> |
Please check out one of the premium Usenet Newsgroup Service Providers below for access to Usenet.