Create ICLR_2020.md (#199)

papers/ICLR_2020.md

+### oral presentation
+1. **CAUSAL DISCOVERY WITH REINFORCEMENT LEARNING** ICLR 2020. [paper](https://arxiv.org/pdf/1906.04477.pdf)
+
+    *Shengyu Zhu, Ignavier Ng, Zhitang Chen*
+
+2. **Posterior sampling for multi-agent reinforcement learning: solving extensive games with imperfect informatio** ICLR 2020. [paper](https://openreview.net/pdf?id=Syg-ET4FPS)
+
+    *Yichi Zhou , Jialian Li, Jun Zhu*
+    
+3. **Harnessing Structures for Value-Based Planning and Reinforcement Learning** ICLR2020. [paper](https://arxiv.org/pdf/1909.12255.pdf)
+
+    *Yuzhe Yang , Guo Zhang, Zhi Xu, Dina Katabi*
+    
+4. **A Closer Look at Deep Policy Gradients** ICLR 2020. [paper](https://openreview.net/pdf?id=ryxdEkHtPS)
+
+    *Andrew Ilyas, Logan Engstrom, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry*
+
+5. **Implementation Matters in Deep RL: A Case Study on PPO and TRPO** ICLR 2020. [paper](https://openreview.net/pdf?id=r1etN1rtPB)
+
+    *Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry*
+    
+6. **A Generalized Training Approach for Multiagent Learning** ICLR 2020. [paper](https://openreview.net/pdf?id=Bkl5kxrKDr)
+
+    *Paul Muller, Shayegan Omidshafiei, Mark Rowland, Karl Tuyls, Julien Perolat, Siqi Liu, Daniel Hennes, Luke Marris, Marc Lanctot, Edward Hughes, Zhe Wang, Guy Lever, Nicolas Heess, Thore Graepel, Remi Munos*
+
+7. **Meta-Q-Learning** ICLR 2020. [paper](https://openreview.net/pdf?id=SJeD3CEFPH)
+
+    *Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola*
+    
+8. **SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference** ICLR 2020. [paper](https://arxiv.org/pdf/1910.06591.pdf)
+
+    *Lasse Espeholt, Raphaël Marinier, Piotr Stanczyk, Ke Wang, Marcin Michalski*