Michael Schaarschmidt

I am a research scientist at DeepMind. I also recently submitted my PhD dissertation in the systems group at the University of Cambridge.

My research focuses on data processing aspects and computer systems applications of deep reinforcement learning. In particular, I am interested in providing controllers for runtime configurations in distributed systems with as little manual modelling as possible. RL is difficult to apply in these domains as problems are both expensive to evaluate (in comparison to typical simulations), and have large discrete action spaces.

Recent work

One of my more useful past projects is TensorForce, a TensorFlow library for applied RL: link

More recently, I have been working on RLgraph, a new software framework for designing and executing RL algorithms at scale: link.

My PhD research is supported by a Google PhD fellowship.

Google scholar profile: link 

I spent summer 2019 working away at DeepMind for further research into systems applications.

Research

  • Wield: Systematic Reinforcement Learning With Progressive Randomization.
    Michael Schaarschmidt, Kai Fricke, Eiko Yoneki, 2019 [pre-print]
  • RLgraph: Modular Computation Graphs for Deep Reinforcement Learning.
    Michael Schaarschmidt, Kai Fricke, Eiko Yoneki Proceedings of the 2nd Conference on Systems and Machine Learning (SysML), Palo Alto, CA, April 2019. [bib] [link] [pre-print]
  • LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations.
    Michael Schaarschmidt, Kai Fricke, Eiko Yoneki, 2018 [bib] [pre-print]
  • Quaestor: Query Web Caching for Database-as-a-Service Providers.
    Felix Gessert*, Michael Schaarschmidt*, Wolfram Wingerath, Erik Witt, Eiko Yoneki, Norbert Ritter *equal contribution Proceedings of the 43rd International Conference on Very Large Databases (PVLDB 2017), Munich, Germany, August 2017. [link]
  • BOAT: Building Auto-Tuners with Structured Bayesian Optimization.
    Valentin Dalibard, Michael Schaarschmidt, Eiko Yoneki Proceedings of the 26th World Wide Web Conference, Systems and Infrastructure track (WWW 2017), Perth, Australia, April 2017. [link]
  • Learning Runtime Parameters in Computer Systems with Delayed Experience Injection.
    Michael Schaarschmidt, Felix Gessert, Valentin Dalibard, Eiko Yoneki Deep Reinforcement Learning Workshop, NIPS 2016, Barcelona, Spain, December 2016. [link]
  • Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization.
    Valentin Dalibard, Michael Schaarschmidt, Eiko Yoneki Workshop on Bayesian Optimization, NIPS 2016, Barcelona, Spain, December 2016. [link]
  • Towards Automated Polyglot Persistence.
    Michael Schaarschmidt, Felix Gessert, Norbert Ritter BTW 2015, Hamburg, Germany, March 2015. [link]
  • The Cache Sketch: Revisiting Expiration-based Caching in the Age of Cloud Data Management.
    Felix Gessert, Michael Schaarschmidt, Steffen Friedich, Norbert Ritter. BTW 2015, Hamburg, Germany, March 2015. [link]
  • Towards a Scalable and Unified REST API for Cloud Data Stores.
    Felix Gessert, Steffen Friedrich, Wolfram Wingerath, Michael Schaarschmidt, Norbert Ritter. Data Management in the Cloud (DMC 2014), Stuttgart, Germany, September 2014. [link]