One often makes trade-offs between these goals, as a result of practical considerations (e.g., computational efficiency); see Table S1 in the Supplementary Material (SUPP) for a brief summary.

Current literature typically assumes that the tasks are diverse, i.e., their parameters uniformly span the

Let Q(v =(v1,v2,..., vd)) = (Q(v1),Q(v2),..., Q(vd)) 12: returnDQ= Q q Theorem 2.Let a 2 (0,1) and 2 (0,1/e) beanyfixedconstants.

Quadratic regression involves modeling the response as a (generalized) linear function of not only the featuresxj, but also of quadratic termsxj1xj2.

Ourapproach, Exploration through Learned Language Abstraction (ELLA) providesintermediate rewards to an agent for completing relevant low-level behaviors as it tries to solve a complex, sparse rewardtask.