Introspection reveals that our meta learned LAs learn through fast association in a way that is qualitatively different from gradientdescent.

Formally, the CCA problem is defined as follows.

In this paper, we establish an upper bound on the return gap between the oracle expert policy and an optimal decision tree policy. This enables us to recast the DT extraction problem into a novel non-euclidean clustering problem over the local observation and action values space of each agent, with action values as cluster labels and the upper bound on the return gap as clustering loss.

Howevb isnon-zero Similarlyr(s, ) are features: r(s, a)= (s, a)>w. Assumption A3(Featureexcitation)Forapolicy withstationarydistributiond (s, a), define =E(s,a) d [ (s, a) (s, a)>].