Deterministic policy gradient algorithmsDavid Silver, Martin Riedmiller, Guy Lever et al.|HAL (Le Centre pour la Communication Scientifique Directe)|2014Cited by 1.7k
Emergence of Locomotion Behaviours in Rich EnvironmentsNicolas Heess, David Silver, Tom Erez et al.|arXiv (Cornell University)|2017Cited by 669
Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse RewardsMartin Riedmiller, Todd Hester, Jonathan Scholz et al.|arXiv (Cornell University)|2017Cited by 510
Graph networks as learnable physics engines for inference and controlÁlvaro Sánchez‐González, Peter Battaglia, Nicolas Heess et al.|arXiv (Cornell University)|2018Cited by 280
Learning an Embedding Space for Transferable Robot SkillsKarol Hausman, Martin Riedmiller, Jost Tobias Springenberg et al.|International Conference on Learning Representations|2018Cited by 190