Direct Experience	MDP			e,T-optimal	O(|S|2|A|T3/e3)	E3 or Rmax (improved)
		e-Approx. Planning	Factoring		Poly(|Factoring|, 1/e,T)	Factored-E3
			local model		O(T |Cover| / e)	Metric-E3
				e-optimal	O(|A||S|T2/e2)	Q-learning
Reset Model	einfinity-regression		einfinity -unmonotone	einfinity / T2,T -optimal	Very Large	Appr. Policy Iter.
			monotone	local optimal	Very Large	Policy Gradient
&mu Reset Model	e/T2-regression	&mu = opt. dist	e2-monotone	e,T-optimal	O(T/e2)	Cons. Policy Iter.
Generative Model					(|A|T/e)O(T)	Sparse Sampling
	e/T-classification				O(|A|T)	RLGen
				e-local-optimal	O(T2)	various
		&mu = opt. dist		Te,T-optimal		PSDP
Deterministic Gen. Model				e local optimal	O(T3 /e2)	Pegasus
Precise Description	MDP			optimal	O(T|S||A|)	Value Iter.
					O(|A||S|)	Policy Iter.

basic setting direct experience reset model generative model precise description