Methods for sequential decision making are often built upon a foundational assumption that the underlying decision process is stationary [Sutton and Barto, 2018]. While this assumption was a cornerstone when laying the theoretical foundations of the field, and while is often reasonable, it isseldom trueinpractice andcanbeunreasonable [Dulac-Arnold etal.,2019].

These selections serve as subgoals that indicate subtasks and guide policy.

Inotherfi( ) with y i > 0 at (x ,y ) contains thesolution.I+(y )torepresenty i > 0. amildassumption Assumption Forany(x ,y )satisfying(3.5), In t f forant (see thedecrease t.

GloVE [25] is a 300-dimensional word embedding space. It is an dimensionality-representation representation of word-word co-occurrence statistics. The FlairNLP repository which we used for the preceding represenations can be found here: https://github.com/flairNLP/ Representations were built using a sliding window of 64 words as a context. Representations were built using a sliding window of 64 words as a context.