Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas
Yen-Ling Kuo,Boris Katz,Andrei Barbu,Yen-Ling Kuo,Boris Katz,Andrei Barbu
We demonstrate a reinforcement learning agent which uses a compositional recurrent neural network that takes as input an LTL formula and determines satisfying actions. The input LTL formulas have never been seen before, yet the network performs zero-shot generalization to satisfy them. This is a novel form of multi-task learning for RL agents where agents learn from one diverse set of tasks and ge...
