Asynchronous Methods for Deep Reinforcement Learning, Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Timothy Harley, David Silver, Koray Kavukcuoglu, 2016Proceedings of the 33rd International Conference on Machine Learning (ICML), Vol. 48 (PMLR)DOI: 10.48550/arXiv.1602.01783 - 介绍了异步优势Actor-Critic (A3C) 及其同步变体 (A2C),展示了它们在深度强化学习任务中的有效性。