EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL. (arXiv:2206.09674v2 [cs.CL] UPDATED)

Reinforcement learning (RL) in long horizon and sparse reward tasks is
notoriously difficult and requires a lot of training steps. A standard solution
to speed up the process is to leverage additional reward signals, shaping it to
better guide the learning process. In the context of language-conditioned RL,
the abstraction and generalisation properties of the language input provide
opportunities for more efficient ways of shaping the reward. In this paper, we
leverage this idea and propose an automated reward shaping …

arxiv language