Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

arXiv:2205.12532v2 Announce Type: replace
Abstract: It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to generalise compositionally to new ones. However, this is a challenging problem due to the curse of dimensionality induced by the combinatorially large number of ways high-level goals can be combined both logically and …

abstract agent agents arxiv cs.lg cs.lo environment language logic machines popular prior reinforcement reinforcement learning skills solve tasks temporal through type