Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning. (arXiv:2201.08115v1 [cs.AI])

The ability to discover behaviours from past experience and transfer them to
new tasks is a hallmark of intelligent agents acting sample-efficiently in the
real world. Equipping embodied reinforcement learners with the same ability may
be crucial for their successful deployment in robotics. While hierarchical and
KL-regularized RL individually hold promise here, arguably a hybrid approach
could combine their respective benefits. Key to these fields is the use of
information asymmetry to bias which skills are learnt. While asymmetric choice …

ai arxiv information learning reinforcement learning