Neural Information Processing Systems http://nips.cc/

However, estimating and optimizingα-divergences require to use importance sampling, which may havelarge orinfinite variance due to heavy tails ofimportance weights.

Thus,γ(ω) (0,1] for ω (0,1], which meets the algorithm design requirement. Algorithm 2 actually performs the gradient descent scheme on the function ˆfti(x) = Eu B[fti(x+ϵu)] restricted to the convex set(1 ζ)K.

Each of these algorithms is described in Table2.

Unlikeknowledge-based anddata-basedalgorithms, competence-based algorithms simultaneously address both the exploration challenge as well as distilling the generated experience in the form of reusable skills.