# recent papers published by DeepMind(2020)

1. **Discovering Reinforcement Learning Algorithms**. [paper link](https://arxiv.org/pdf/2007.08794.pdf)

    *Junhyuk Oh, Matteo Hessel, Wojciech M. Czarnecki, Zhongwen Xu, Hado van Hasselt, Satinder Singh, David Silver* 
    
2. **Revisiting Fundamentals of Experience Replay**. [paper link](http://acsweb.ucsd.edu/~wfedus/pdf/replay.pdf)

    *William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua Bengio, Hugo Larochelle, Mark Rowland, Will Dabney* 
    
3. **Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion**. [paper link](https://kstatic.googleusercontent.com/files/e787c4727f6dc7694e6b71d8582a71012716d2e7ed4687797b92b69cb187af61685fdb8918fdb83cf772d846dd28960b46ee4a6ed9af5bad2cc5cb7ac25065c2)

    *Roland Hafner, Tim Hertweck, Philipp Kloppner, Michael Bloesch, Michael Neunert, Markus Wulfmeier, Saran Tunyasuvunakool, Nicolas Heess, Martin Riedmiller* 
   
4. **Agent57: Outperforming the Atari Human Benchmark**. [paper link](https://arxiv.org/pdf/2003.13350.pdf)

    *Adrià Puigdomènech Badia,  Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitsky, Daniel Gu, Charles Blundel* 

5. **Hyperparameter Selection for Offline Reinforcement Learning**. [paper link](https://arxiv.org/pdf/2007.09055.pdf)

    *Tom Le Paine, Cosmin Paduraru, Andrea Michi , Caglar Gulcehre , Konrad Żołna, Alexander Novikov , Ziyu Wang and Nando de Freitas*

6. **Importance Weighted Policy Learning and Adaption**. [paper link](https://arxiv.org/pdf/2009.04875.pdf)

    *Alexandre Galashov, Jakub Sygnowski, Guillaume Desjardins, Jan Humplik, Leonard Hasenclever, Rae Jeong, Yee Whye Teh, Nicolas Heess*