/explore
|
You are here 
|
handsandcities.com | ||
| | | | |
www.greaterwrong.com
|
|
| | | | | I wrote this post during my scholarship at MATS. My goal is to describe a research direction of the learning theoretic agenda (LTA). Namely, a natural infra-Bayesian learning algorithm proposal that arguably leads to Pareto-optimal solutions in repeated games. The idea originates from Vanessa, I'm expanding a draft of her into a more accessible description. The expected audience are people who are interested in ongoing work on LTA. It is especially suitable for people who are looking for a research direction to pursue in this area. | |
| | | | |
www.greaterwrong.com
|
|
| | | | | In this post, I describe two major obstacles for logical inductor decision theory: untaken actions are not observable and no updatelessness for computations. I will concretely describe both of these problems in a logical inductor framework, but I believe that both issues are general enough to transcend that framework. Consider the following formalization of the 5 and 10 problem: Let {Pn} is a logical inductor. Let An be an agent which uses this logical inductor, to output either 5 or 10 as follows. The utility function Un for agent An is simply Un=An/10, and the source code for agent An is given by An={5if EPnn(Un|An=5)>EPnn(Un|An=10)10otherwise. | |
| | | | |
joecarlsmith.com
|
|
| | | | | First in a two-part series about whether morality falls out instrumental rationality, if you do the game-theory right. This part lays out of the basic structure of a prominent argument in favor. | |
| | | | |
futurism.com
|
|
| | | Perplexity CEO Aravind Srinivas is using the troubling rise in AI companionship apps to hawk his company's AI web browser. | ||
