%0 Journal Article
%T Accidental exploration through value predictors
%A Kisielewski, Tomasz
%A Leśniak, Damian
%J Schedae Informaticae
%V 2018
%R 10.4467/20838476SI.18.009.10414
%N Volume 27
%P 107-127
%K reinforcement learning, value predictors, exploration
%@ 1732-3916
%D 2018
%U https://ejournals.eu/en/journal/schedae-informaticae/article/accidental-exploration-through-value-predictors
%X 
	Infinite length of trajectories is an almost universal assumption in the theoretical foundations of reinforcement learning. In practice learning occurs on finite trajectories. In this paper we examine a specific result of this disparity, namely a strong bias of the time-bounded Every-visit Monte Carlo value estimator. This manifests as a vastly different learning dynamic for algorithms that use value predictors, including encouraging or discouraging exploration. We investigate these claims theoretically for a one dimensional random walk, and empirically on a number of simple environments. We use GAE as an algorithm involving a value predictor and evolution strategies as a reference point.