Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods. (arXiv:2201.12126v1 [cs.AI])

Web: http://arxiv.org/abs/2201.12126

Enabling reinforcement learning (RL) agents to leverage a knowledge base
while learning from experience promises to advance RL in knowledge intensive
domains. However, it has proven difficult to leverage knowledge that is not
manually tailored to the environment. We propose to use the subclass
relationships present in open-source knowledge graphs to abstract away from
specific objects. We develop a residual policy gradient method that is able to
integrate knowledge across different abstraction levels in the class hierarchy.
Our method results …

ai arxiv gradient learning policy reinforcement learning