Add three papers

Weight Normalization : A Simple Reparameterization to Accelerate
Training of Deep Neural Networks

Continuous Deep Q-Learning with Model-based Acceleration

Deep Reinforcement Learning from Self-Play in Imperfect-Information
Games

Author: muupan

README.md

@@ -57,6 +57,9 @@ If you want to inform the maintainer of a new paper, feel free to contact [@mooo
  - T. Zahavy, N. Ben Zrihem, and S. Mannor, **Graying the black box: Understanding DQNs**, arXiv, 2016. [arXiv](http://arxiv.org/abs/1602.02658)
  - J. N. Foerster, Y. M. Assael, N. de Freitas, and S. Whiteson, **Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks**, arXiv, 2016. [arXiv](http://arxiv.org/abs/1602.02672)
  - I. Osband, C. Blundell, A. Pritzel, and B. Van Roy, **Deep Exploration via Bootstrapped DQN**, arXiv, 2016. [arXiv](http://arxiv.org/abs/1602.04621)
+ - T. Salimans and D. P. Kingma, **Weight Normalization : A Simple Reparameterization to Accelerate Training of Deep Neural Networks**, arXiv, 2016. [arXiv](http://arxiv.org/abs/1602.07868)
+ - S. Gu, T. Lillicrap, I. Sutskever, and S. Levine, **Continuous Deep Q-Learning with Model-based Acceleration**, arXiv, 2016. [arXiv](http://arxiv.org/abs/1603.00748)
+ - J. Heinrich and D. Silver, **Deep Reinforcement Learning from Self-Play in Imperfect-Information Games David Silve**, arXiv, 2016. [arXiv](http://arxiv.org/abs/1603.01121)
 
 ### Deep Policy