Michael Gimelfarb

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 16

Top Topics

Continuous State Spaces

Nonlinear Programming

Reinforcement Learning

Top Venues

Publications

Michael Gimelfarb, Ayal Taitler, Scott Sanner
Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs. CoRR (2024)
Ayal Taitler, Ron Alford, Joan Espasa, Gregor Behnke, Daniel Fiser, Michael Gimelfarb, Florian Pommerening, Scott Sanner, Enrico Scala, Dominik Schreiber, Javier Segovia-Aguas, Jendrik Seipp
The 2023 International Planning Competition. AI Mag. 45 (2) (2024)
Michael Gimelfarb, Ayal Taitler, Scott Sanner
JaxPlan and GurobiPlan: Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous Probabilistic Domains. ICAPS (2024)
Michael Gimelfarb, Michael Jong Kim
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions. CoRR (2023)
Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, Scott Sanner
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization. ICLR (2023)
Ayal Taitler, Michael Gimelfarb, Sriram Gopalakrishnan, Xiaotian Liu, Scott Sanner
pyRDDLGym: From RDDL to Gym Environments. CoRR (2022)
Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, Scott Sanner
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization. CoRR (2022)
Michael Gimelfarb, André Barreto, Scott Sanner, Chi-Guhn Lee
Risk-Aware Transfer in Reinforcement Learning using Successor Features. NeurIPS (2021)
Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Contextual policy transfer in reinforcement learning domains via deep mixtures-of-experts. UAI (2021)
Michael Gimelfarb, André Barreto, Scott Sanner, Chi-Guhn Lee
Risk-Aware Transfer in Reinforcement Learning using Successor Features. CoRR (2021)
Noah Patton, Jihwan Jeong, Michael Gimelfarb, Scott Sanner
RAPTOR: End-to-end Risk-Aware MDP Planning and Policy Learning by Backpropagation. CoRR (2021)
Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Contextual Policy Reuse using Deep Mixture Models. CoRR (2020)
Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Bayesian Experience Reuse for Learning from Multiple Demonstrators. CoRR (2020)
Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning. CoRR (2020)
Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Epsilon-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning. UAI (2019)
Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach. NeurIPS (2018)