Scribd Logo
Upload

Welcome to Scribd!

  • 54 views

    Xue Bin (Jason) Peng: Year 2, PHD in Computer Science

    Uploaded by

    lays cleo
    This document is a CV for Jason Peng that summarizes his education and awards, publications, work experience, and technical skills. It shows that he received multiple academic honors and scholarships during his undergraduate and graduate studies. It lists several publications in top conferences on using deep reinforcement learning for skills like locomotion. It also provides details on his work experience at companies like OpenAI, Adobe, Disney, Microsoft, and Capcom, where he worked on projects involving graphics, simulation, and machine learning. Finally, it outlines his proficiency in languages like C++ and Python as well as software like Visual Studio and version control tools.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Xue Bin (Jason) Peng: Year 2, PHD in Computer Science

    Uploaded by

    lays cleo
    54 views3 pages
    This document is a CV for Jason Peng that summarizes his education and awards, publications, work experience, and technical skills. It shows that he received multiple academic honors and scholarships during his undergraduate and graduate studies. It lists several publications in top conferences on using deep reinforcement learning for skills like locomotion. It also provides details on his work experience at companies like OpenAI, Adobe, Disney, Microsoft, and Capcom, where he worked on projects involving graphics, simulation, and machine learning. Finally, it outlines his proficiency in languages like C++ and Python as well as software like Visual Studio and version control tools.

    Original Description:

    jason's cv

    Original Title

    Jason Peng Cv

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document is a CV for Jason Peng that summarizes his education and awards, publications, work experience, and technical skills. It shows that he received multiple academic honors and scholarships during his undergraduate and graduate studies. It lists several publications in top conferences on using deep reinforcement learning for skills like locomotion. It also provides details on his work experience at companies like OpenAI, Adobe, Disney, Microsoft, and Capcom, where he worked on projects involving graphics, simulation, and machine learning. Finally, it outlines his proficiency in languages like C++ and Python as well as software like Visual Studio and version control tools.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    54 views3 pages

    Xue Bin (Jason) Peng: Year 2, PHD in Computer Science

    Uploaded by

    lays cleo
    This document is a CV for Jason Peng that summarizes his education and awards, publications, work experience, and technical skills. It shows that he received multiple academic honors and scholarships during his undergraduate and graduate studies. It lists several publications in top conferences on using deep reinforcement learning for skills like locomotion. It also provides details on his work experience at companies like OpenAI, Adobe, Disney, Microsoft, and Capcom, where he worked on projects involving graphics, simulation, and machine learning. Finally, it outlines his proficiency in languages like C++ and Python as well as software like Visual Studio and version control tools.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    Xue Bin (Jason) Peng

    Year 2, PhD in Computer Science


    [email protected]
    xbpeng.github.io
    EDUCATION/AWARDS
     PhD in Computer Science, University of California, Berkeley 2017–Present
    - NSERC Postgraduate Scholarship
    - Berkeley Fellowship For Graduate Study
     MSc in Computer Science, University of British Columbia 2015 –2017
    - Governor-General’s Gold Medal
    o top of master’s class across all faculties (~2000 students)
    - NSERC Canada Graduate Scholarship Master’s Award
    - Theodore E Arnold Fellowship
    - CS Merit Award
     Computer Science Honours, University of British Columbia 2010 – 2015
    - Governor-General’s Silver Medal in Science
    o top of undergrad class in faculty of science (~2000 students)
    - Grade average: 95.6 %
    - Norman A M MacKenzie Scholarship
    - President’s Entrance Scholarship
    - Trek Excellence Scholarship
    - Greer Family Scholarship
    - Charles and Jane Banks Scholarship
    - Marie Kendall Memorial Scholarship in Science
    - Computer Science Scholarship
     School of Interactive Arts and Technology, Simon Fraser University 2009 – 2010
    - Gordon M. Shrum Scholarship

    PUBLICATIONS
    Refereed Journals/Conferences
     Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, and Sergey Levine. SFV:
    Reinforcement Learning of Physical Skills from Videos. ACM Transactions on Graphics (Proc.
    SIGGRAPH Asia 2018) 37, 6 (2018).
     Xue Bin Peng, Pieter Abbeel, Sergey Levine, and Michiel van de Panne. DeepMimic: Example-
    Guided Deep Reinforcement Learning of Physics-Based Character Skills. ACM Transactions on
    Graphics (Proc. SIGGRAPH 2018) 37, 4 (2018).
     Xue Bin Peng, Marcin Andrychowicz, Wojciech Zaremba, and Pieter Abbeel. Sim-to-Real
    Transfer of Robotic Control with Dynamics Randomization. IEEE International Conference on
    Robotics and Automation (ICRA) (2018).
     Xue Bin Peng, Glen Berseth, KangKang Yin, and Michiel van de Panne. DeepLoco: Dynamic
    Locomotion Skills Using Hierarchical Deep Reinforcement Learning. ACM Transactions on
    Graphics (Proc. SIGGRAPH 2017) 36, 4 (2017).
     Xue Bin Peng, and Michiel van de Panne. Learning Locomotion Skills Using DeepRL: Does the
    Choice of Action Space Matter? Proc. ACM SIGGRAPH / Eurographics Symposium on
    Computer Animation (2017). Best student paper.
     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Terrain-adaptive locomotion skills using
    deep reinforcement learning. ACM Transactions on Graphics (Proc. SIGGRAPH 2016) 35, 4
    (2016).
     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Dynamic Terrain Traversal Skills Using
    Reinforcement Learning. ACM Transactions on Graphics (Proc. SIGGRAPH 2015) 34, 4 (2015).

    Non-Refereed
     Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, and Sergey Levine. Variational
    Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining
    Information Flow. arXiv preprint arXiv:1810.00821 (2018).

    Posters and Abstracts


     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Learning Locomotion Skills Using
    DeepRL: Does the Choice of Action Space Matter? NIPS Deep Reinforcement Learning
    Workshop, (2016).
     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Terrain-adaptive locomotion skills using
    deep reinforcement learning. NIPS Deep Learning Symposium, (2016).
     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Dynamic Locomotion Across Variable
    Terrains Using Deep Reinforcement Learning. Dynamic Walking, (2016).
     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Dynamic Locomotion Skills for
    Obstacle Sequences Using Reinforcement Learning. Dynamic Walking, (2015).
     Xue Bin Peng, Glen Berseth, and Michiel van de Panne. Learning Dynamic Locomotion Skills
    for Terrains with Obstacles. Reinforcement Learning and Decision Making, (2015).

    WORK EXPERIENCE
    Member of Technical Staff (Intern), OpenAI May – Aug, 2017
     Explored methods for transferring control policies from simulation to a physical robot

    Research Assistant, University of British Columbia 2015 - 2017


     Developed methods to train motion control policies for physics-based character simulation

    Graduate Teaching Assistant, University of British Columbia Jan – April 2017


     Hosted office hours
     Wrote code for assignments
     Graded assignments and exams

    Research Intern, Adobe Research May – Aug, 2015


     Explored methods for physically-plausible motion control of simulated characters

    Lab Associate (Intern), Disney Research Pittsburgh Jan – May, 2015


     Developed models of human gameplay strategies through imitation learning
     Instrumented game to collect player data

    Undergraduate Teaching Assistant, University of British Columbia 2011 - 2014


     Directed labs and hosted office hours
     Wrote code for assignments
     Graded assignments and exams

    Intern Software Developer, Microsoft Studios May – Nov, 2013


     Developed real-time analytic approximation of area lights with different BRDFs
     Implemented clustered forward lighting
     Implemented environment map volumes and parallax correction

    Co-op Rendering Engineer, Capcom Vancouver Jan – Aug, 2012


     Designed and created various rendering features through HLSL and C++
     Designed a system for physically inspired image based lighting, utilizing real-time generation of
    dynamic environment maps
     Implemented subsurface scattering for skin, distance field text and decal rendering, vertex
    animation, deferred lights, HDR cubemap support for Maya, and a variety of post-effects

    TECHNICAL SKILLS
    Programming Languages : Software :
     Most fluent: C++, Python, Matlab,  Microsoft Visual Studio
     C#, HLSL/GLSL, Java, Haskell, Prolog  Photoshop
     Git
     Perforce

    You might also like