Marcus Hutter: What is AIXI? | AI Podcast Clips

(more links below)

Podcast full episodes playlist:

Podcasts clips playlist:

Podcast website:

Podcast on Apple Podcasts (iTunes):

Podcast on Spotify:

Podcast RSS:

Marcus Hutter is a senior research scientist at DeepMind and professor at Australian National University. Throughout his career of research, including with Jürgen Schmidhuber and Shane Legg, he has proposed a lot of interesting ideas in and around the field of artificial general intelligence, including the development of the AIXI model which is a mathematical approach to AGI that incorporates ideas of Kolmogorov complexity, Solomonoff induction, and reinforcement learning.

Subscribe to this YouTube channel or connect on:

[qflqzjg]

1:32 So a Barcelona's church was Marcus "reinforcement learning agent" for validating AIXI, stone engraved all those decades or hundreds of years ago.
2:06 In Chinese, 爱惜 (àixī) may be translated as _cherish, value, prize or treasure_ and, indeed, 2:33, in Japanase the same character 愛 (traditional) means *love* as in Chinese.
Since AIXI maximizes the expected total rewards from the environment, it literally loves going after the *prize* 🤣

[SamSpade]

If the model were perfect the Markov assumption would be fine, but reality is too complex... you've got to accumulate heuristics.