Lemma 7, p. 19 — the conservative policy loses at most ξ/(1−γ) in its own MDP: V̂^π − V̂^{π̂c} ≤ ξ/(1−γ)

Initializing...

Lemma 7, p. 19 — the conservative policy loses at most ξ/(1−γ) in its own MDP: V̂^π − V̂^{π̂c} ≤ ξ/(1−γ) · Prove2Me