My resume can also be found as a PDF and on LinkedIn, but both are slightly out-of-date.


Graduate: UC Berkeley (2020 - Present)
  • Pursuing a PhD in Computer Science.
  • Gratefully supported by a NSF GRFP fellowship and a Berkeley fellowship.

Undergraduate: UC Berkeley (2015 - 2019)
  • Double major in Computer Science (honors) and Applied Mathematics (honors).
  • GPA: 3.99 / 4.00
  • Dean's List from Fall 2015 - present
  • Relevant Courses: Machine Learning, Convex Optimization, Artificial Intelligence, Theoretical Statistics, Algorithms, Computer Architecture, Randomized Algorithms, Data Structures . Full list here


  • An operator view of policy gradient methods
    Dibya Ghosh, Marlos C. Machado, Nicolas Le Roux.
    NeurIPS 2020. Arxiv
  • Representations for Stable Off-Policy Reinforcement Learning
    Dibya Ghosh, Marc G. Bellemare.
    ICML 2020. Arxiv
  • On Catastrophic Interference in Atari 2600 Games
    William Fedus*, Dibya Ghosh*, John D. Martin, Marc G. Bellemare, Yoshua Bengio, Hugo Larochelle.
    NeurIPS 2019 Workshop on Biological and Artificial RL. Arxiv
  • Learning To Reach Goals Without Reinforcement Learning
    Dibya Ghosh*, Abhishek Gupta*, Justin Fu, Ashwin Reddy, Coline Devin, Benjamin Eysenbach, Sergey Levine.
  • Learning Actionable Representions with Goal-Conditioned Policies
    Dibya Ghosh, Abhishek Gupta, Sergey Levine.
    ICLR 2019. Arxiv
  • Variational Inverse Control with Events
    Justin Fu, Avi Singh, Dibya Ghosh, Larry Yang, Sergey Levine.
    NeurIPS 2018. Arxiv
  • Divide-and-Conquer Reinforcement Learning
    Dibya Ghosh, Avi Singh, Aravind Rajeswaran, Vikash Kumar, Sergey Levine.
    ICLR 2018. Arxiv
  • Theory Meets Data
    Ani Adhikari, (editor: Dibya Ghosh), et al.
    PDF (Last updated 01/2017)


AI Resident at Google Brain, Montréal (July 2019 - July 2020)
  • Performing fundamental research in reinforcement learning and optimization.
Head Undergraduate Student Instructor for UC Berkeley Statistics (Jan 2017 - June 2019) Lead Developer at Preminon Inc (Dec 2016 - Dec 2018)
  • Working with < cloaked > in deployment of machine learning toolkits for alternative architectures
Research Assistant at Lawrence Berkeley National Laboratory (June 2016 - June 2019)
  • Working under the supervision of Dr. Benjamin Brown at Lawrence Berkeley National Laboratory (Brown Lab)
  • Focused on developing interpretable and explainable machine learning algorithms for analyzing high-dimensional scientific systems, such as genomics and agriculture.
Course Developer at UC Berkeley (June 2016 - Dec 2016)
  • Worked with Ani Adhikari and Jason Zhang to develop and design curriculum for Statistics 140: Probability for Data Science.
  • Co-wrote the prob140 library with Jason Zhang, a data science library geared toward probability theory written for Prob140 in Python. The library supports graphical visualization and computational tools for finite, infinite, joint, and continuous probability distributions as well as Markov Chains and other random processes.
  • Prototyped and fleshed out labs, projects, and other instructional material
  • Designed build system and pipeline for prototyping HW assignments and deployment to students
  • Worked closely with Jupyter and Gradescope to optimize student submission of assignments
Visualization Lead for the Berkeley Institute for Data Science (Feb 2016 - June 2016)
  • Data Science Community Visualization for the Annual Ecosystem Report @ BIDS
  • Applying unsupervised learning techniques to find graph clusters and identify communities of and topics in data science research.
  • Managed the front-end development with D3.JS and AngularJS
  • Responsbile for integration with internal pipeline through Flask, Mongo DB, and MySQL.
Course Development Assistant for Data 8 at UC Berkeley (Jan 2016 - May 2016)
  • Developing the backend for materials and datasets in use for the pioneering Data Science class (500 students)
  • Responsibilities involved exploring appropriate datasets for course materials, running preliminary statistical analyses of datasets, designing examples to include in the textbook, Computational and Inferential Thinking, and developing exercises to include in practice sets or assignments.

Awards and Honors

  • Best Student Paper Award at NeurIPS 2019 BARL workshop (out of 30 papers)
  • Awarded the Berkeley Fellowship (given to the top incoming PhD students at UC Berkeley)
  • Awarded the NSF GRFP Fellowship (given to 2000 / 13000 applications)
  • CS Major Citation (awarded to the top graduating senior in Computer Science)
  • Outstanding Graduate Student Instructor Award (awarded to top 10% of GSIs)
  • Finalist for CRA Outstanding Undergraduate Researcher Award (awarded to ~20 students nationally)
  • Quantedge Award for Academic Excellence (awarded to ~120 seniors at UC Berkeley)
  • 3rd Place worldwide at Intel International Science Fair 2015 in Bioinformatics / Computational Biology
  • Dean's Honor List (top 4% at UC Berkeley) for Fall 2015, Spring 2016, Fall 2016, Spring 2017, Fall 2017
  • 1st Place in Pacman AI competition for CS 188 in Summer 2016
  • Robert J. Kraft Award for Freshmen (awarded to ~ 300 people in the 9000-person freshman class)
  • Intel Award for Computer Science (best CS related project at CCCSEF)
  • Chevron Award for Innovation (best project at CCCSEF)