benefits and curse of POMDP

observation does not improve predictive power

exponential growth if we discretize state space

observation does improve predictive power

Reinforcement learning

use neural networks to partially estimate outcomes at higher dimensions, somewhat side-stepping the Curse of Dimensionality

static

unknown properties don’t change over time

dynamic

unknown properties may change over time

partially observed Markov Decision Process

like an Markov Decision Process on the belief space