Meta Learning and Self Play - Ilya Sutskever, OpenAI (YouTube), 2017 OpenAI - Meta Learning & Self Play - Ilya Sutskever (YouTube), 2018 Ilya Sutskever: OpenAI Meta-Learning and Self-Play (YouTube), 2018
《Meta-Learning with Memory-Augmented Neural Networks》 论文地址：https://proceedings.mlr.press/v48/santoro16.pdf 《Prototypical Networks for Few-shot Learning》 论文地址：https://arxiv.org/abs/1703.05175 《Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks》 论文地址：https://proceedings.mlr.press/v70/finn17a/finn17a.pdf
《Human-level concept learning through probabilistic program induction》 论文地址：https://amygdala.psychdept.arizona.edu/labspace/JclubLabMeetings/Lijuan-Science-2015-Lake-1332-8.pdf 《Neural Architecture Search with Reinforcement Learning》 论文地址：https://arxiv.org/pdf/1611.01578 《A Simple Neural Attentive Meta-Learner》 论文地址：https://arxiv.org/pdf/1707.03141
《Hindsight Experience Replay》 论文地址：https://arxiv.org/abs/1707.01495 《Continuous control with deep reinforcement learning》 论文地址：https://arxiv.org/abs/1509.02971 《Sim-to-Real Transfer of Robotic Control with Dynamics Randomization》 论文地址：https://arxiv.org/abs/1710.06537 《Meta Learning Shared Hierarchies》 论文地址：https://arxiv.org/abs/1710.09767 《Temporal Difference Learning and TD-Gammon ，1995》 论文地址：https://www.csd.uwo.ca/~xling/cs346a/extra/tdgammon.pdf 《Karl Sims - Evolved Virtual Creatures, Evolution Simulation, 1994》 论文地址：https://dl.acm.org/doi/10.1145/192161.192167 《Emergent Complexity via Multi-Agent Competition》 论文地址：https://arxiv.org/abs/1710.03748 《Deep reinforcement learning from human preferences》 论文地址：https://arxiv.org/abs/1706.03741
Yann LeCun 等人的工作，他在 CNN 的实际应用方面做出了开创性的工作 ——《Gradient-based learning applied to document recognition》 Ian Goodfellow 等人的工作，他在生成对抗网络（GAN）方面的工作长期主导了图像生成领域 ——《Generative Adversarial Networks》 Demis Hassabis 等人的工作，他在 AlphaFold 方面的强化学习研究获得了诺贝尔奖 ——《Human-level control through deep reinforcement learning》、《AlphaFold at CASP13》
