Skip to content

Jonathan Sorg

  • PhD Candidate in Computer Science
  • University of Michigan
  • 7h-indexImpact measure calculated using publication and citation counts. Updated daily.
  • 93CitationsNumber of citations received by Jonathan's publications. Updated daily.

Other IDs

Research interests

Intrinsic MotivationTemporal/State AbstractionReinforcement Learning

Co-authors (3)

  • Jeshua Bratman

Publications (5)

  • Optimal Rewards versus Leaf-Evaluation Heuristics in Planning Agents

    • Sorg J
    • Singh S
    • Lewis R
    N/AReaders
    N/ACitations
  • The Optimal Reward Problem: Designing Effective Reward for Bounded Agents

    • Sorg J
    N/AReaders
    N/ACitations
  • Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective

    • Singh S
    • Lewis R
    • Barto A
    • et al.
    N/AReaders
    N/ACitations
  • Reward Design via Online Gradient Ascent

    • Sorg J
    • Singh S
    • Lewis R
    N/AReaders
    N/ACitations
  • Variance-Based Rewards for Approximate Bayesian Reinforcement Learning

    • Sorg J
    • Singh S
    • Lewis R
    N/AReaders
    N/ACitations

Professional experience

PhD Candidate in Computer Science

The University of Michigan

January 2008 - Present

Education

PhD in Computer Science

The University of Michigan

January 2008 - Present

MS in Computer Science

The University of Michigan

August 2005 - December 2007(2 years)

BS in Computer Science

Northwestern University

September 2001 - June 2005(4 years)