Clement Gehring

PhD Student
Learning and Intelligent Systems Group
MIT CSAIL
${lastname} at csail.mit.edu


Research

I am a PhD student in the Learning and Intelligent Systems Group in MIT CSAIL with Professors Tomas Lozano-Perez and Leslie Pack Kaelbling.

Conference Publications

  • Clement Gehring, Leslie Pack Kaelbling, Tomas Lozano-Perez. Adaptable replanning with compressed linear action models for learning from demonstrations. Proceedings of the Conference on Robot Learning (CoRL). 2018. [paper][code][video]
  • Zi Wang, Clement Gehring, Pushmeet Kohli, Stefanie Jegelka. Batched Large-scale Bayesian Optimization in High-dimensional Spaces. Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS). 2018.
  • Clement Gehring, Yangchen Pan, Martha White. Incremental Truncated LSTD. Proceedings of the 2016 International Joint Conference on Artificial Intelligence (IJCAI). 2016. [paper] [code]
  • Clement Gehring, Doina Precup. Smart exploration in reinforcement learning using absolute temporal difference errors. Proceedings of the 2013 international conference on Autonomous Agents and Multi-Agent Systems (AAMAS). International Foundation for Autonomous Agents and Multiagent Systems, 2013. [paper]

Archive Publications

  • Zi Wang, Clement Gehring, Pushmeet Kohli, Stefanie Jegelka. Ensemble Bayesian Optimization.arXiv:1706.01445. 2017. [paper]

Workshop Publications

  • Zi Wang, Clement Gehring, Pushmeet Kohli, Stefanie Jegelka. Batched Large-scale Bayesian Optimization in High-dimensional Spaces. NIPS Workshop on Bayesian Optimization (BAYESOPT). 2017. [paper]
  • Anwarissa Asbah*, André MS Barreto*, Clement Gehring*, Joelle Pineau, and Doina Precup. Reinforcement Learning Competition: Helicopter Hovering with Controllability and Kernel-Based Stochastic Factorization. In Proceedings of International Conference on Machine Learning (ICML), Reinforcement Learning Competition Workshop. 2013. [paper]

Extended Abstract

  • Clement Gehring. Approximate Linear Successor Representation. The multi-disciplinary conference on Reinforcement Learning and Decision Making (RLDM). 2015. [paper]

Other Publications

  • Caelan R. Garrett*, Clement Gehring*, Gustavo Goretkin*, Zelda Mariet*, Zi Wang*. Motion Planning using Naturally Annoying Grammars (NAGs), SIGTBD, 2016. [paper]