Yoav Ravid | v1.5.0Mar 24th 2022 | (+4/-4) | ||
plex | v1.4.0Oct 22nd 2021 | made pagename bold | ||
habryka | v1.3.0Mar 10th 2021 | |||
SamDeere | v1.2.0Nov 20th 2020 | (+11/-9) | ||
Ruby | v1.1.0Oct 12th 2020 | (+33) | ||
abramdemski | v1.0.0Aug 27th 2020 | (+466) |
See the Infra-BaseniasmBayesianism Sequence.
Infra-Bayesianism is a new approach to epistemology / decision theory / reinforcement learning theory, which builds on "imprecise probability" to solve the problem of prior misspecification / grain-of-truth / nonrealizability which plagues Bayesianism and Bayesian reinforcement learning.
Infra-Bayesianism also naturally leads to an implementation of UDT, and (more speculatively at this stage) has applications to multi-agent theory, embedded agency and reflection.
Infra-Bayesianism also naturally leads to an implementation of
UDT,UDT, and (more speculatively at this stage) has applications to multi-agent theory, embedded agency and reflection.