Michael Gimelfarb

19 papers A* 5A 2Journal 11Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Bounded-Error Policy Optimization for Mixed Discrete-Continuous MDPs via Constraint Generation in Nonlinear Programming. CPAIOR (1) Michael Gimelfarb, Ayal Taitler, Scott Sanner
2025	A*	`conf`	ModelDiff: Symbolic Dynamic Programming for Model-Aware Policy Transfer in Deep Q-Learning. AAAI Xiaotian Liu, Jihwan Jeong, Ayal Taitler, Michael Gimelfarb, Scott Sanner
2025	J	`jnl`	STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation. CoRR Hossein Goli, Michael Gimelfarb, Nathan Samuel de Lara, Haruki Nishimura, Masha Itkina, Florian Shkurti
2024	J	`jnl`	Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs. CoRR Michael Gimelfarb, Ayal Taitler, Scott Sanner
2024	A*	`conf`	JaxPlan and GurobiPlan: Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous Probabilistic Domains. ICAPS Michael Gimelfarb, Ayal Taitler, Scott Sanner
2024	J	`jnl`	The 2023 International Planning Competition. AI Mag. 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
2023	A*	`conf`	Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization. ICLR Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, Scott Sanner
2023	J	`jnl`	Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions. CoRR Michael Gimelfarb, Michael Jong Kim
2022	J	`jnl`	Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization. CoRR Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, Scott Sanner
2022	J	`jnl`	pyRDDLGym: From RDDL to Gym Environments. CoRR Ayal Taitler, Michael Gimelfarb, Sriram Gopalakrishnan, Xiaotian Liu, Scott Sanner
2021	A	`conf`	Contextual policy transfer in reinforcement learning domains via deep mixtures-of-experts. UAI Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
2021	J	`jnl`	RAPTOR: End-to-end Risk-Aware MDP Planning and Policy Learning by Backpropagation. CoRR Noah Patton, Jihwan Jeong, Michael Gimelfarb, Scott Sanner
2021	A*	`conf`	Risk-Aware Transfer in Reinforcement Learning using Successor Features. NeurIPS Michael Gimelfarb, André Barreto, Scott Sanner, Chi-Guhn Lee
2021	J	`jnl`	Risk-Aware Transfer in Reinforcement Learning using Successor Features. CoRR Michael Gimelfarb, André Barreto, Scott Sanner, Chi-Guhn Lee
2020	J	`jnl`	Bayesian Experience Reuse for Learning from Multiple Demonstrators. CoRR Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
2020	J	`jnl`	Contextual Policy Reuse using Deep Mixture Models. CoRR Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
2020	J	`jnl`	ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning. CoRR Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
2019	A	`conf`	Epsilon-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning. UAI Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
2018	A*	`conf`	Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach. NeurIPS Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee