LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Pashootan Vaezipoor, Andrew C. Li, Rodrigo Toro Icarte, Sheila A. McIlraith

Abstract: We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language {–} linear ...