The workshop basically included any form of future state optimization, mainly including Causal Entropic Forces and Empowerment approaches.
It was very interesting to meet and know the really few people out there caring about this concept of maximizing some entropy measure -actually it always boiled down to a mutual information measurement- that will be happening in the future.
 |
| Speakers and organizers |
If I had to summarize my impressions in a single thought, it may well be that all approaches we were discussing initially take the form of an elegant concept with an intractable formulation, but, ultimately they all can be cracked down to a simpler form, then applied to some real world problems with amazing results.
That said, the most intriguingly truth I learnt in Graz is that this hot-spicy-wine thing they drink all over the city places at night, do smell like teenager's used socks, but you eventually get used to it, and even enjoy!
 |
| Guillem painfully trying to get used to it |
Guillem prepared these slides with really nice videos of Fractal AI solving some Montezuma rooms while my slides focused more on the theoretical grounds of FAI.
300k samples of MsPacman using a FractalAI Swarm. Each point corresponda to the UMAP embedding of frames, and the red line corresponds to the game displayed in the right part of the screen. pic.twitter.com/fXQd8us2NA— Guillem Duran (@Miau_DB) December 18, 2019
No comments:
Post a Comment