Guiding reinforcement learning exploration using natural language

In this work we present a technique for using natural language to help reinforcement learning generalize to unseen environments using neural machine translation techniques. These techniques are then integrated into policy shaping to make it more effective at learning in unseen environments. We evaluate this technique using the popular arcade game, Frogger, and show that our modified policy shaping algorithm improves over a Q-learning agent as well as a baseline version of policy shaping.