Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to solve sparse reward tasks entirely from scratch. More often, we might possess prior experience to draw on that provides considerable guidance about which actions and outcomes are possible in the world, which we can use to explore more effectively for new tasks. In this work, we study how prior data without reward labels may be used to guide and accelerate exploration for an agent solving a new sparse reward task. We propose a simple approach that learns a reward model from online experience, labels the unlabeled prior data with optimistic rewards, and then uses it concurrently alongside the online data for downstream policy and critic optimization. This general formula leads to rapid exploration in several challenging sparse-reward domains where tabula rasa exploration is insufficient, including the AntMaze domain, Adroit hand manipulation domain, and a visual simulated robotic manipulation domain. Our results highlight the ease of incorporating unlabeled prior data into existing online RL algorithms, and the (perhaps surprising) effectiveness of doing so.

翻译：从稀疏奖励信号中学习解决任务是标准强化学习（RL）算法面临的主要挑战。然而在现实世界中，智能体很少需要完全从零开始解决稀疏奖励任务。更常见的情况是，我们可能拥有可借鉴的先验经验，这些经验能提供关于世界中哪些动作和结果可行的实质性指导，从而帮助我们在新任务中更有效地进行探索。本研究探讨了如何利用无奖励标签的先验数据来引导和加速智能体解决新稀疏奖励任务的探索过程。我们提出了一种简单方法：从在线经验中学习奖励模型，用乐观奖励标记无标签先验数据，然后将其与在线数据同时用于下游策略和评论家优化。这一通用公式在多个具有挑战性的稀疏奖励领域（包括AntMaze域、Adroit手部操作域和视觉模拟机器人操作域）中实现了快速探索，而这些领域中从头开始探索是远远不够的。我们的研究结果突显了将无标签先验数据融入现有在线RL算法的简便性，以及这样做（或许令人惊讶的）有效性。