- Abstract: Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems. However, it still often suffers from the need to engineer a reward function that not only reflects the task but is also carefully shaped. This limits the applicability of RL in the real world. It is therefore of great practical importance to develop algorithms which can learn from unshaped, sparse reward signals, e.g. a binary signal indicating successful task completion. We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents. Our method complements the recently proposed hindsight experience replay (HER) by inducing an automatic exploratory curriculum. We evaluate our approach on the tasks of reaching various goal locations in an ant maze and manipulating objects with a robotic arm. Each task provides only binary rewards indicating whether or not the goal is completed. Our method asymmetrically augments these sparse rewards for a pair of agents each learning the same task, creating a competitive game designed to drive exploration. Extensive experiments demonstrate that this method leads to faster converge and improved task performance.
- Keywords: reinforcement learning, sparse reward, goal-based learning
- TL;DR: a novel method to learn with sparse reward using adversarial reward re-labeling