Michael Gimelfarb
Scholar

Michael Gimelfarb

Google Scholar ID: 1tBgyLYAAAAJ
Department of Computer Science, University of Toronto
Artificial IntelligenceMachine LearningDeep LearningReinforcement LearningRobotics
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
227
 
H-index
8
 
i10-index
7
 
Publications
19
 
Co-authors
26
list available
Contact
Emailmike.gimelfarb@mail.utoronto.caCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
2 items
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
2025
Cited
0
Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs
arXiv.org · 2024
Cited
0
Resume (English only)
Academic Achievements
  • June 2025: Paper on 'trajectory stitching using diffusion models' accepted to RobotEvaluation@RSS 2025
  • May 2025: Paper on 'bounded error policy optimization' accepted to CPAIOR2025; paper on 'symbolic DP for policy transfer' published in AAAI2025
  • March 2024: Results of the 2023 International Planning Competition published in AI Magazine
  • February 2024: Released pyRDDLGym version 2.0
  • February 2024: Paper on 'JaxPlan and GurobiPlan' published in ICAPS
Co-authors
26 total
Scott Sanner
Scott Sanner
University of Toronto
Chi-Guhn Lee
Chi-Guhn Lee
University of Toronto
Co-author 3
Co-author 3
Jihwan Jeong
Jihwan Jeong
Google Research
Daniel Fišer
Daniel Fišer
Aalborg University
Gregor Behnke
Gregor Behnke
ILLC - University of Amsterdam
Enrico Scala
Enrico Scala
Università di Brescia
Co-author 8
Co-author 8