Optimistic AIXI (Sunehag and Hutter)

Added by Deon Garrett about 7 years ago

We consider extending the AIXI agent by using multiple (or even a compact class of) priors. This has the benefit of weakening the conditions on the true environment that we need to prove asymptotic optimality. Furthermore, it decreases the arbitrariness of picking the prior or reference machine. We connect this to removing symmetry between accepting and rejecting bets in the rationality axiomatization of AIXI and replacing it with optimism. Optimism is often used to encourage exploration in the more restrictive Markov Decision Process setting and it alleviates the problem that AIXI (with geometric discounting) stops exploring prematurely.

paper_24.pdf (180 kB)

Replies (1)

RE: Optimistic AIXI (Sunehag and Hutter) - Added by Adena Mccullough 13 days ago

On some sites, there are a list of enormous topics that are broader in sense and usage as well. Hence, I am suggesting that https://bestwritingclues.com/reviews/ukessays-review/ this link will give you all the effective criteria to fulfill and provide benefits to others.