Machine Super Intelligence

This thesis concerns the optimal behaviour of agents in unknown computable environments, also known as universal artificial intelligence. These theoretical agents are able to learn to perform optimally in many types of environments. Although they are able to optimally use prior information about the environ- ment if it is available, in many cases they also learn to perform optimally in the absence of such information. Moreover, these agents can be proven to upper bound the performance of general purpose computable agents. Clearly such agents are extremely powerful and general, hence the name universal artificial intelligence.