Woah, Andrew, this is fantastic work! I am seriously excited about this direction.! I liked your previous posts on boundaries very much too, but I had no idea your thoughts on boundaries were this technically refined—and that they tie in so beautifully with Markov blankets!
re: Friston.
Friston particular style that could justifiably be called obscurantist. His writing is extremely verbose, often fails to define key terms, and very nontrivial equations are often posited without derivation or citation. After spending considerable effort trying to understand the rather lofty prose I would often realize the key ideas were indeed quite interesting—but could be explained far better. There are some big claims in his work but insufficiently many details are worked out to ascertain to what degree this claims can be justified. A group of people have taken up the thankless task of Friston exegesis but unfortunately have not really developed a sufficiently clear & crisp account. The book you cite is an example of this literature. Long story short I am excited that your recent work might finally resolve this cloud of confusion!
In the context of this post, the following paper is particularly relevant:
Nevertheless, inside there is a definition of a decomposition of a Markov blanket & boundary into action, observation, internal and external states that seems extra similar to your story [but I think you’ve gone much farther already!]. I talked a little about Friston’s decomposition of Markov Boundaries recently for the MetaUni Abstraction seminar, see here for the relevant slide.
If anyone is interested in joining a learning community around the ideas of active inference, the mission of https://www.activeinference.org/ is to educate the community around these topics. There’s a study group around the 2022 active inference textbook by Parr, Friston, and Pezzulo. I’m in the 5th cohort and it’s been very useful for me.
Woah, Andrew, this is fantastic work! I am seriously excited about this direction.! I liked your previous posts on boundaries very much too, but I had no idea your thoughts on boundaries were this technically refined—and that they tie in so beautifully with Markov blankets!
re: Friston.
Friston particular style that could justifiably be called obscurantist. His writing is extremely verbose, often fails to define key terms, and very nontrivial equations are often posited without derivation or citation. After spending considerable effort trying to understand the rather lofty prose I would often realize the key ideas were indeed quite interesting—but could be explained far better. There are some big claims in his work but insufficiently many details are worked out to ascertain to what degree this claims can be justified. A group of people have taken up the thankless task of Friston exegesis but unfortunately have not really developed a sufficiently clear & crisp account. The book you cite is an example of this literature. Long story short I am excited that your recent work might finally resolve this cloud of confusion!
In the context of this post, the following paper is particularly relevant:
https://royalsocietypublishing.org/doi/10.1098/rsif.2013.0475
Apart from being very unclear, almost deliberately so, apparently it also has actual serious errors.
Nevertheless, inside there is a definition of a decomposition of a Markov blanket & boundary into action, observation, internal and external states that seems extra similar to your story [but I think you’ve gone much farther already!]. I talked a little about Friston’s decomposition of Markov Boundaries recently for the MetaUni Abstraction seminar, see here for the relevant slide.
If anyone is interested in joining a learning community around the ideas of active inference, the mission of https://www.activeinference.org/ is to educate the community around these topics. There’s a study group around the 2022 active inference textbook by Parr, Friston, and Pezzulo. I’m in the 5th cohort and it’s been very useful for me.