Our approach relies on the principle ofoptimism under uncertaintyto efficiently explore. Our learning algorithms optimizetheiractions withrespect toamodel based ontheempirical statistics, while optimistically overestimating rewards and underestimating the resource consumption (i.e., overestimating the distance from the constraint).

In this paper we study instruction following in text-based games and propose an approach that advances theprevious stateoftheart.

In contrast, the mathematics needed to analyze such schemes is what forms the focus in Stochastic Approximation (SA) theory [2, 4]. More generally, SA refers to an iterative scheme that helps find zeroes or optimal points of a function, for which only noisy evaluationsarepossible.

Most existing results only focus on online settings, in which agents can interact with the environment during training.

Thenfor N ( log (de H/ ))sufficientlylarge, withprobability1 , wehave (b ;!)= O