Demonstrations are widely used in Deep Reinforcement Learning (DRL) for facilitating solving tasks with sparse rewards. However, the tasks in real-world scenarios can often have varied initial conditions from the demonstration, which would require additional prior behaviours. For example, consider we are given the demonstration for the task of \emph{picking up an object from an open drawer}, but the drawer is closed in the training. Without acquiring the prior behaviours of opening the drawer, the robot is unlikely to solve the task. To address this, in this paper we propose an Intrinsic Rewards Driven Example-based Control \textbf{(IRDEC)}. Our method can endow agents with the ability to explore and acquire the required prior behaviours and then connect to the task-specific behaviours in the demonstration to solve sparse-reward tasks without requiring additional demonstration of the prior behaviours. The performance of our method outperforms other baselines on three navigation tasks and one robotic manipulation task with sparse rewards. Codes are available at https://github.com/Ricky-Zhu/IRDEC.

翻译：演示（Demonstrations）在深度强化学习（Deep Reinforcement Learning, DRL）中被广泛用于促进稀疏奖励任务的求解。然而，现实场景中的任务通常可能具有与演示不同的初始条件，这需要额外的先验行为。例如，假设我们获得了“从打开的抽屉中拾取物体”任务的演示，但训练时抽屉是关闭的。若没有获取打开抽屉的先验行为，机器人不太可能解决该任务。为解决这一问题，本文提出了一种基于内在奖励驱动的示例控制方法\textbf{(IRDEC)}。我们的方法能够赋予智能体探索并获取所需先验行为的能力，进而将其与演示中的任务特定行为相连接，从而在不需额外演示先验行为的情况下解决稀疏奖励任务。在三个导航任务和一个具有稀疏奖励的机器人操作任务中，我们的方法性能优于其他基线方法。代码可在 https://github.com/Ricky-Zhu/IRDEC 获取。