Publications
Publications
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
Hossein Goli, Michael Gimelfarb, Nathan Samuel Lara, Masha Itkina, Haruki Nishimura, and Florian Shkurti
Robot Evaluation for the Real World, 2025
Bounded-Error Policy Optimization for Mixed Discrete-Continuous MDPs via Constraint Generation in Nonlinear Programming
Michael Gimelfarb, Ayal Taitler, and Scott Sanner
In Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 2025
ModelDiff: Symbolic Dynamic Programming for Model-Aware Policy Transfer in Deep Q-Learning
Xiaotian Liu, Jihwan Jeong, Ayal Taitler, Michael Gimelfarb, and Scott Sanner
In Proceedings of the AAAI Conference on Artificial Intelligence, 2025
The 2023 International Planning Competition
Ayal Taitler, Ron Alford, Joan Espasa, Gregor Behnke, Daniel Fišer, Michael Gimelfarb, Florian Pommerening, Scott Sanner, Enrico Scala, Dominik Schreiber, and others
AI Magazine, 2024
JaxPlan and GurobiPlan: Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous Probabilistic Domains
Michael Gimelfarb, Ayal Taitler, and Scott Sanner
In Proceedings of the International Conference on Automated Planning and Scheduling, 2024
ModelDiff: Leveraging Models for Policy Transfer with Value Lower Bounds
Xiaotian Liu, Jihwan Jeong, Ayal Taitler, Michael Gimelfarb, and Scott Sanner
In PRL Workshop Series: Bridging the Gap Between AI Planning and Reinforcement Learning, 2024
Conservative bayesian model-based value expansion for offline policy optimization
Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, and Scott Sanner
In International Conference on Learning Representations, 2023
pyRDDLGym: From RDDL to Gym Environments
Ayal Taitler, Michael Gimelfarb, Jihwan Jeong, Sriram Gopalakrishnan, Martin Mladenov, Xiaotian Liu, and Scott Sanner
In PRL Workshop Series: Bridging the Gap Between AI Planning and Reinforcement Learning, 2023
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions
Michael Gimelfarb, and Michael Jong Kim
arXiv preprint arXiv:2305.07844, 2023
A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs
Noah Patton, Jihwan Jeong, Michael Gimelfarb, and Scott Sanner
In Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Contextual policy transfer in reinforcement learning domains via deep mixtures-of-experts
Michael Gimelfarb, Scott Sanner, and Chi-Guhn Lee
In Uncertainty in Artificial Intelligence, 2021
Bayesian experience reuse for learning from multiple demonstrators
Michael Gimelfarb, Scott Sanner, and Chi-Guhn Lee
In International Joint Conference on Artificial Intelligence, 2021
Risk-aware transfer in reinforcement learning using successor features
Michael Gimelfarb , André Barreto, Scott Sanner, and Chi-Guhn Lee
In Advances in Neural Information Processing Systems, 2021
Epsilon-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning
Michael Gimelfarb, Scott Sanner, and Chi-Guhn Lee
In Uncertainty in Artificial Intelligence, 2020
Reinforcement learning with multiple experts: A bayesian model combination approach
Michael Gimelfarb, Scott Sanner, and Chi-Guhn Lee
In Advances in neural information processing systems, 2018