Mohamad H Danesh

I am a research engineer at Ivy, working on unifying existing ML frameworks. Prior to that, I was a research intern at the National University of Singapore, working with Panpan Cai and Professor David Hsu on planning under uncertainty for autonomous vehicles. I got my master’s from the Oregon State University, where I was advised by Professor Alan Fern working on explainable and robust reinforcement learning.

My research interest broadly lies in reinforcement learning. I have researched explainability in RL, robust and safe RL, and now I am currently working on planning and learning under uncertainty.

Selected Publications

  1. LEADER: Learning Attention Over Driving Behaviors For Planning Under Uncertainty
    Mohamad H Danesh, Panpan Cai, and David Hsu
    In 6th Annual Conference on Robot Learning 2022 (oral) (best paper awards finalist)
    arXiv PDF Code Talk Webpage
  2. Re-understanding Finite-State Representations of Recurrent Policy Networks
    Mohamad H Danesh, Anurag Koul, Alan Fern, and Saeed Khorram
    In International Conference on Machine Learning 2021
    arXiv PDF Code Talk
  3. Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results
    Mohamad H Danesh, and Alan Fern
    In International Conference on Machine Learning, UDL Workshop 2021 (oral)
    arXiv PDF Benchmark Code Baseline Code Talk
  4. Stochastic Block-ADMM for Training Deep Networks
    Saeed Khorram, Xiao Fu, Mohamad H Danesh, Zhongang Qi, and Li Fuxin
    arXiv preprint arXiv:2105.00339 2021
    arXiv PDF

Notes and Summaries

A summary of the “Mathematics for ML” book
A summary of the “AI A modern approach” book