Exploiting Contextual Structure to Generate Useful Auxiliary Tasks

arXiv:2303.05038v2 Announce Type: replace-cross
Abstract: Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We propose an approach that maximizes experience reuse while learning to solve a given task by generating and simultaneously learning useful auxiliary tasks. To generate these tasks, we construct an abstract temporal logic representation of the given task and leverage large language models to generate context-aware …

abstract arxiv cs.ai cs.lg cs.ro environment environmental experience generate reinforcement reinforcement learning robots solve tasks type work