1. Continuous control with deep reinforcement learning;lillicrap;arXiv 1509 02971,2015
2. RLlib: Abstractions for distributed reinforcement learning;liang;Proc 35th Int Conf Mach Learn (ICML),2018
3. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor;haarnoja;Proc 35th Int Conf Mach Learn (ICML),2018
4. Proximal policy optimization algorithms;schulman;arXiv 1707 06347,2017
5. Knowledge-Defined Networking