I am a PhD student in computational and mathematical engineering (ICME) at Stanford University advised by Emma Brunskill in CS department. My research is mainly focused on deep reinforcement learning.
I enjoy hiking, reading evolutionary biology and learning French.

Honors & Awards

  • iCME departmental fellowship, Stanford University (2015)
  • Silver medal of group competition at 5th IOAA, IOAA (2011)
  • Bronze medal of 5th International Olympiad in Astronomy and Astrophysics, IOAA (2011)

Education & Certifications

  • BSc, Sharif University of Technology, Mechanical Engineering, Minor of Economics (2015)

Service, Volunteer and Community Work

  • PSA Board Member, Persian Student Assosciation (April 1, 2015 - Present)

    The Persian Student Association (PSA) is a non-political voluntary student organization whose objective is to sponsor Persian social and cultural activities and events, to promote an understanding of Persian culture, to help foster friendship among different cultural groups, and to provide a source of union and support for the Persian community at Stanford.



Personal Interests

Backpacking, Reading NYT, Listening to Arctic Monkeys and Pink Floyd

Current Research and Scholarly Interests

Reinforcement Learning, Deep Learning, Human in the Loop Reinforcement Learning

Work Experience

  • Data Science, Intern, StitchFix (June 15, 2016 - September 9, 2016)


    San Fransisco

All Publications

  • Significant contribution of small icebergs to the freshwater budget in Greenland fjords. Communications earth & environment Rezvanbehbahani, S., Stearns, L. A., Keramati, R., Shankar, S., van der Veen, C. J. 2020; 1 (1): 31


    Icebergs represent nearly half of the mass loss from the Greenland Ice Sheet and provide a distributed source of freshwater along fjords which can alter fjord circulation, nutrient levels, and ultimately the Meridional Overturning Circulation. Here we present analyses of high resolution optical satellite imagery using convolutional neural networks to accurately delineate iceberg edges in two East Greenland fjords. We find that a significant portion of icebergs in fjords are comprised of small icebergs that were not detected in previously-available coarser resolution satellite images. We show that the preponderance of small icebergs results in high freshwater delivery, as well as a short life span of icebergs in fjords. We conclude that an inability to identify small icebergs leads to inaccurate frequency-size distribution of icebergs in Greenland fjords, an underestimation of iceberg area (specifically for small icebergs), and an overestimation of iceberg life span.

    View details for DOI 10.1038/s43247-020-00032-3

    View details for PubMedID 33184615

  • Value Driven Representation for Human-in-the-Loop Reinforcement Learning Keramati, R., Brunskill, E., Assoc Comp Machinery ASSOC COMPUTING MACHINERY. 2019: 176–80